JP7417466B2 - Information processing device, information processing method, and information processing program - Google Patents

Description

The present invention relates to an information processing device, an information processing method, and an information processing program.

2. Description of the Related Art Conventionally, there has been a technology for detecting guardrails on the shoulders of roads. The technology described in Patent Document 1 detects a group of reflection points when reflected by an object (reflection point) in response to irradiating radar waves, and clusters the reflection points included in the reflection point group. Generate a group. The technique described in Patent Document 1 outputs clusters that satisfy guardrail conditions among clusters included in a cluster group as guardrails.

JP2019-027973A

The technique described in Patent Document 1 detects guardrails, and does not detect other terrestrial objects other than guardrails. However, in addition to guardrails, various features such as cushion drums and rubber poles are arranged on roads. For example, when creating a road map, it may be desirable to detect various other features in addition to guardrails.

An object of the present invention is to provide an information processing device, an information processing method, and an information processing program for estimating features placed on a road.

An information processing device in one embodiment includes a first acquisition unit that acquires point cloud data generated by measuring reflection points reflected by an object by irradiating a laser onto the ground surface; and a first acquisition unit that acquires point cloud data. a classification unit that classifies the ground surface into a road surface and a non-road surface based on the point cloud data obtained by the classification unit; and a classification unit that classifies the ground surface into a road surface and a non-road surface based on the point cloud data, and a reflection point that is adjacent to each other within a predetermined distance for the point cloud data that is classified as a non-road surface by the classification unit. an estimating unit that estimates a feature based on the characteristics of the point cloud made up of a plurality of grouped reflection points, and an output unit that outputs the feature estimated by the estimating unit. Be prepared.

In one embodiment of the information processing device, the estimation unit selects one processing point from among the plurality of reflection points as a first point of interest, and the first point of interest is different from the first point of interest among the plurality of reflection points. Calculating distances to other processing points, selecting other processing points whose calculated distance is less than or equal to a first threshold, and grouping the selected first point of interest and a plurality of other processing points. Good too.

In one embodiment of the information processing device, the estimation unit may not perform grouping if the number of the selected first point of interest and the plurality of other processing points is equal to or less than a second threshold.

In one aspect of the information processing device, the estimating unit may associate the shape of a preset feature with the shape of the feature, and when the point cloud and the shape are associated, the estimation unit may estimate the point group as a feature with that shape. good.

In one aspect of the information processing device, when the point cloud is associated with a preset cylindrical shape, the estimating unit estimates one of the cushion drum and the rubber pole as a feature according to the size of the point cloud. You can also do it.

In one embodiment of the information processing device, the estimation unit performs clustering by grouping reflection points that vary in a transverse direction that intersects the extension direction, among the plurality of reflection points that exist along the extension direction of the road. , the clustered reflection points may be used as a point group to be estimated as vegetation as a terrestrial feature if they correspond to a preset distribution of feature points of vegetation.

An information processing device in one aspect includes a second acquisition unit that acquires image data obtained by imaging the surroundings including the ground surface, and the classification unit includes, in addition to the point cloud data acquired by the first acquisition unit, The ground surface may be classified into a road surface and a non-road surface based on the image data acquired by the second acquisition unit.

In one embodiment of the information processing device, the estimation unit acquires the color of the feature based on the image data acquired by the second acquisition unit, and estimates the feature based on the acquired color of the feature. Good too.

In one aspect of the information processing method, a first acquisition step includes a first acquisition step in which a computer acquires point cloud data generated by measuring reflection points reflected by an object by irradiating a laser onto the ground surface; A classification step of classifying the ground surface into a road surface and a non-road surface based on the point cloud data obtained in the step; and a classification step that classifies the ground surface as a road surface and a non-road surface based on the point cloud data that are adjacent to each other within a predetermined distance. an estimation step of estimating a feature based on the characteristics of the point cloud, which is made up of a plurality of grouped reflection points; and an output step of outputting the feature estimated by the estimation step. and execute.

An information processing program in one aspect includes a first acquisition function that acquires point cloud data generated by measuring reflection points reflected by an object by irradiating a laser onto the ground surface; A classification function that classifies the ground surface into a road surface and a non-road surface based on the point cloud data acquired by the function, and a classification function that classifies the ground surface as a road surface and a non-road surface based on the point cloud data acquired by the function, and a classification function that classifies the ground surface as a non-road surface based on the point cloud data that is adjacent to each other within a predetermined distance. An estimation function that groups each reflection point and estimates a feature based on the characteristics of the grouped multiple reflection points as a point cloud, and an output function that outputs the feature estimated by the estimation function. and make it come true.

An information processing device in one embodiment acquires point cloud data measured by irradiating a laser onto the ground surface, classifies the ground surface into a road surface and a non-road surface based on the point cloud data, and classifies the ground surface into a road surface and a non-road surface. Point cloud data classified as surfaces is grouped into adjacent points within a predetermined distance, and features are estimated based on the characteristics of the grouped reflection points (point clouds). Since objects are output, it is possible to provide the results of estimating features placed on roads.
The information processing method and information processing program of one embodiment can produce the same effects as the information processing device of one embodiment described above.

FIG. 2 is a block diagram for explaining an information processing device. FIG. 3 is a diagram for explaining a point group in a surrounding area including the ground surface. FIG. 3 is a diagram for explaining a cushion drum. FIG. 2 is a diagram for explaining vegetation. 1 is a flowchart for explaining an information processing method according to an embodiment.

An embodiment of the present invention will be described below.
Although the wording "information" is used in this specification, the wording "information" can be rephrased as "data" and the wording "data" can be rephrased as "information."

FIG. 1 is a block diagram for explaining the information processing device 1. As shown in FIG.
FIG. 2 is a diagram for explaining a point group 201 in a surrounding area including the ground surface.

As shown in FIG. 1, the information processing device 1 stores point cloud data (a plurality of point clouds 201 (see FIG. 2)) of a surrounding area including the ground surface, and image data obtained by imaging the area. Based on this, features 300 (for example, cushion drum 300a, rubber pole 300b, vegetation 300c, etc.) on the shoulder of the road on which the vehicle is traveling are estimated.
By estimating the feature 300, the information processing device 1 can identify the position of the feature 300 as the road shoulder edge 400 (see FIG. 2), and can also identify the location of the feature 300 or the road shoulder edge 400 as the road shoulder edge 400. It becomes possible to register in map information related to maps. The road shoulder edge 400 indicates, for example, a stopping limit when a vehicle makes an emergency stop.

Point cloud data is obtained by scanning a surrounding area including the ground surface with a laser (emitted light) and receiving the laser (reflected light) reflected by an object in the area. That is, the point cloud data is constituted by data of a plurality of reflection points (point clouds) of laser beams. The surrounding region including the ground surface may include, for example, a region below (the ground surface) as well as a region laterally (to the sides) relative to the ground. Further, the surrounding area including the ground surface may include, for example, an upper area in addition to the above-mentioned lower and side areas. The image data is generated by a camera unit that images the surrounding area including the ground surface. For example, point cloud data and image data can be obtained by a mobile mapping system that includes a three-dimensional laser metrology machine and a digital camera.

Next, the information processing device 1 will be explained in detail.
The information processing device 1 includes a communication section 17 , a storage section 18 , a display section 19 , a first acquisition section 12 , a second acquisition section 13 , a classification section 14 , an estimation section 15 , and an output control section 16 . The first acquisition unit 12, the second acquisition unit 13, the classification unit 14, the estimation unit 15, and the output control unit 16 may be implemented as a function of the control unit 11 (for example, an arithmetic processing unit, etc.) of the information processing device 1. good.

The communication unit 17 is capable of transmitting and receiving information to and from devices outside the information processing device 1 (for example, the server 100, etc.). The communication unit 17 may read out information (point cloud data and image data) obtained by the mobile mapping system from the server 100 under the control of the control unit 11 .

The storage unit 18 stores various information and programs. The storage unit 18 stores map information regarding road maps. Further, the storage unit 18 may temporarily or non-temporarily store the point cloud data and image data acquired from the server 100 by the communication unit 17.

The display unit 19 is, for example, a device that can display characters, images, and the like.

The first acquisition unit 12 acquires point cloud data measured by irradiating the ground surface with a laser. That is, the first acquisition unit 12 acquires, for example, point cloud data measured by a mobile mapping system. The first acquisition unit 12 acquires point cloud data measured in a specific area (road) in which a feature 300 on the shoulder of a road or the like is desired to be specified. As an example, the first acquisition unit 12 (control unit 11) may specify a specific area and then acquire point cloud data of the specific area.

The second acquisition unit 13 acquires image data obtained by imaging the surrounding area including the ground surface. That is, the second acquisition unit 13 acquires, for example, image data generated by a mobile mapping system. The second acquisition unit 13 acquires image data of the same specific area (road) where the point cloud data acquired by the first acquisition unit 12 was measured.

Note that, for example, the mobile mapping system may associate point cloud data and image data for each measurement location. Alternatively, for example, the server 100 may associate point cloud data and image data for each measurement location of the mobile mapping system. This allows the information processing device 1 to acquire point cloud data and image data at the same location. In this case, when the point cloud data of the specified specific area is acquired in the first acquisition unit 12 (control unit 11), the second acquisition unit 13 (control unit 11) acquires an image of the same area (specific area). It is also possible to obtain data.
In the case of this embodiment, the first acquisition unit 12 and the second acquisition unit 13 are described as having different functions (two blocks), but as another embodiment, the first acquisition unit 12 and the second acquisition unit 13 are described as having different functions (two blocks). may have the same function (one block).

The classification unit 14 classifies the ground surface into a road surface and a non-road surface based on the point cloud data acquired by the first acquisition unit 12. The classification unit 14 may classify the point group 201 (reflection points 201a) located in the same plane among the point group data into road surfaces.
For example, the classification unit 14 may classify point cloud data that is within a predetermined distance from a certain plane (within a predetermined range regarding vertical height) as the ground surface. The classification unit 14 can set various distances as the predetermined distance, and can set a distance within a predetermined range in the vertical direction as the predetermined distance, taking into account unevenness on the surface of the road. For example, the classification unit 14 can set any vertical distance such as 5 cm, 10 cm, 15 cm, and 20 cm as the processing distance. That is, the classification unit 14 may, for example, classify a plane made up of reflection points 201a that fall within a predetermined distance in the vertical direction as a road surface.

The classification unit 14 may classify the point group 201 (reflection points 201b) that is not classified as a road surface as a non-road surface. The classification unit 14 classifies a reflection point 201b as a non-road surface based on the fact that the laser is reflected by a feature 300 (for example, objects on the shoulder of a road such as a cushion drum 300a, a rubber pole 300b, and vegetation 300c). do. In addition to the above-mentioned example of the feature 300, the classification unit 14 also includes various features (for example, guardrails, guard cables, road side walls, soundproof walls, differences in level between the road and the sidewalk, and road slopes). ) may be classified as a non-road surface.

The classification unit 14 is not limited to classifying into road surfaces and non-road surfaces using only point cloud data as described above. Based on the image data acquired by the second acquisition unit 13, the ground surface may be classified into a road surface and a non-road surface. If the feature 300 is recorded in the image data, the classification unit 14 can understand the feature 300 using the image data. That is, the classification unit 14 can classify the ground surface (the surrounding area including the ground surface) into a road surface and a non-road surface, for example, based on point cloud data and image data.

The estimation unit 15 groups the point cloud data classified as non-road surfaces by the classification unit 14 into mutually adjacent point groups 201 (reflection points 201b) within a predetermined distance, and divides the grouped reflection points 201c (Fig. 3 and 4)). In this case, the estimation unit 15 selects one processing point among the reflection points 201b as the first point of interest 211 (see FIG. 3), and selects the first point of interest 211 and the first point of interest 211 among the reflection points 201b. calculates the distance from another different processing point (other point of interest 212 (see FIG. 3)), selects another processing point for which the calculated distance is less than or equal to the first threshold, and selects the selected first point of interest. 211 and a plurality of other processing points may be grouped together. On the other hand, the estimation unit 15 may not perform grouping if the number (total number) of the selected first point of interest 211 and a plurality of other processing points is less than or equal to the second threshold.

FIG. 3 is a diagram for explaining the cushion drum 300a.
More specifically, the estimation unit 15 groups reflection points 201b classified as non-road surfaces. In this case, the estimation unit 15 creates, for example, a kd-tree from the reflection points 201b (processing target points) to be grouped. A kd-tree is a space-partitioned data structure that classifies points existing in space.
First, the estimation unit 15 performs cluster determination. In this cluster determination, the estimation unit 15 selects one point (first point of interest 211) from the point group to be processed and adds it to the checklist, and also selects one point (first point of interest 211) from the point group to be processed and adds it to the checklist. One point (other points of interest 212) is selected. The estimation unit 15 calculates the distance between the first point of interest 211 and another point of interest 212. If the calculated distance is less than or equal to the first threshold, the estimation unit 15 adds another point of interest 212 to the checklist. The estimation unit 15 identifies the plurality of points of interest added to the checklist as one cluster. The estimation unit 15 removes the points of interest identified as clusters (point group 201 (reflection points 201b)) from the processing target point group, and performs the above-described processing until clusters are identified in all point groups (reflection points) 201. repeat. The estimation unit 15 removes clusters in which the number of points of interest (point groups (reflection points) 201) constituting the clusters identified through the above processing is equal to or less than the minimum number of elements (second threshold).

The first threshold is a length that allows one feature 300 to be grouped as a cluster. A specific example of the first threshold value may be a value such as 5 cm, 10 cm, 15 cm, or 20 cm, or a value other than these.
The minimum number of elements (second threshold) is a value that is appropriately set in the estimation unit 15 according to the estimation target feature 300, for example, in order to group clusters and estimate them as one feature 300. A specific example of the minimum number of elements may be a value such as 10, 20, 30, 40, or 50, or a value other than these.

The estimation unit 15 associates the grouped reflection points 201c (point group) with the shape of the feature 300 set in advance, and when the reflection points 201c (point group) and the shape are associated, It may also be estimated as the terrestrial feature 300 having that shape.

For example, when the grouped reflection points 201c (point cloud) are associated with a preset cylindrical shape, the estimation unit 15 determines the size of the reflection points 201c (point cloud) as the feature 300. It is also possible to estimate one of the cushion drum 300a and the rubber pole 300b. As a specific example, the estimation unit 15 applies cylinder model segmentation of the library Point Cloud Library for 3D point cloud processing to the cushion drum 300a and the rubber pole 300b, and adjusts parameters such as radius and central axis direction. It can be estimated by

That is, the cushion drum 300a and the rubber pole 300b generally have a cylindrical shape. Therefore, the estimation unit 15 can estimate the cushion drum 300a and the rubber pole 300b by performing cylindrical fitting on the grouped reflection points 201c (point group) and acquiring the radius and axis direction. .
Further, as an example, the diameter of the cushion drum 300a is about 580 mm, and the diameter of the rubber pole 300b is often about 80 mm. Therefore, the estimating unit 15 may distinguish between the cushion drum 300a and the rubber pole 300b by setting a threshold value for distinguishing between the cushion drum 300a and the rubber pole 300b in the radius described above.

Furthermore, the estimation unit 15 applies the above-described cylinder model segmentation to cylinder fitting. In this case, the estimation unit 15 can also obtain the direction vector 220 (see FIG. 3) of the central axis of the cylinder. The central axes of the cushion drum 300a and the rubber pole 300b are often perpendicular to the road surface. Therefore, if the direction vector 220 of the central axis of the cylinder obtained by fitting is perpendicular to the road surface, the estimation unit 15 may estimate the cylinder as the cushion drum 300a and the rubber pole 300b.

Note that during the above estimation, the estimation unit 15 sets a threshold value for the height of the grouped reflection points 201c (point group) (fitted cylinder), and determines that the height of the fitted cylinder is If it is below the threshold value, it may be estimated as the cushion drum 300a and the rubber pole 300b. As an example, since the heights of the cushion drum 300a and the rubber pole 300b are limited to several types, the above-mentioned height threshold may be set for the highest one.

FIG. 4 is a diagram for explaining the vegetation 300c.
The estimation unit 15 groups reflection points 201b that vary in the transverse direction (road width direction W) intersecting the extension direction among the plurality of reflection points 201b existing along the extension direction of the road. If clustering is performed and the clustered reflection points 201c (point group) correspond to a preset distribution of feature points of the vegetation 300c, it may be estimated as the vegetation 300c as the feature 300. . As a specific example, the estimation unit 15 sets a location where the reflection points 201b projected from the sky vary in the width direction W of the road as a vegetation presence candidate location, and the image of that location is detected as a feature point using a method such as Harris corner detection. It is possible to calculate the vegetation 300c, and to estimate that the vegetation 300c matches the feature point distribution that is known in advance to be the vegetation 300c.

The estimation unit 15 may acquire the color of the feature 300 based on the image data acquired by the second acquisition unit 13, and estimate the color of the feature 300 based on the acquired color of the feature 300. For example, when the feature 300 is a cushion drum 300a, the color of the feature 300 is yellow or orange, and has a yellow and black striped pattern or checkered pattern, or an orange and silver striped pattern or checkered pattern, etc. has been added. For example, when the feature 300 is a rubber pole 300b, the color of the feature 300 is yellow, orange, or green, and a silver striped pattern or a yellow and black striped pattern is added. For example, when the feature 300 is vegetation 300c, the color becomes green, for example. In addition to the example of the terrestrial feature 300 described above, colors (characteristic colors) are assigned to each of various terrestrial features. The estimation unit 15 may estimate the feature 300 based on the respective characteristics of the point cloud data and the color of the feature 300 recorded in the image data.

Furthermore, the estimation unit 15 may estimate the shape (features) of the feature 300 using image data in addition to point cloud data. For example, when the feature 300 is recorded in image data, the estimation unit 15 can estimate the shape of the feature 300 recorded in the image data. For example, the estimation unit 15 can estimate the shape of the feature 300 using a learning model that has learned the shape of the feature 300, pattern matching, or the like. The estimating unit 15 may estimate the feature 300 based on the point cloud data, the shape of the feature 300, and the color of the feature 300 recorded in the image data.
Note that the estimating unit 15 may not only estimate the cushion drum 300a, the rubber pole 300b, and the vegetation 300c as the terrestrial objects 300, as in the example described above, but may also estimate various terrestrial objects.

The output control unit 16 controls the output unit to output the feature 300 estimated by the estimation unit 15. The output section may be, for example, the display section 19 or the storage section 18. For example, the output control unit 16 may display the feature 300 estimated by the estimation unit 15 on the display unit 19. In this case, the output control unit 16 may display on the display unit 19 the position of the feature 300 superimposed on the road map based on the map information. Further, for example, the output control unit 16 may store information regarding the feature 300 estimated by the estimation unit 15 in the storage unit 18. Further, the output section may be the communication section 17. In this case, for example, the output control unit 16 may control the communication unit 17 to transmit information regarding the feature 300 estimated by the estimation unit 15 to the outside (for example, the server 100 etc.).

The control unit 11 may specify the road shoulder edge 400 (see FIG. 2) based on the position of the feature 300 estimated by the estimation unit 15. That is, the control unit 11 may specify the position of the feature 300 estimated by the estimation unit 15 as the shoulder edge 400 of the road. The road shoulder edge 400 indicates, for example, a stopping limit when a vehicle makes an emergency stop.
In this case, the control unit 11 determines that among the plurality of features 300 estimated by the estimation unit 15, if there are a plurality of features 300 in a direction intersecting the road extension direction (road width direction W), The boundary (position) of the feature 300 located closest to the center of the road may be the road shoulder edge 400 (see FIG. 2). As an example, on the shoulder of a road, there may be a guardrail or rubber pole 300b at a position closer to the center of the road, and vegetation 300c behind it (at a position farther from the center of the road). Even when there are a plurality of features 300 in the width direction W of the road, the control unit 11 determines the position of the feature 300 closest to the center of the road in the width direction W of the road. 400.

The control unit 11 may register the road shoulder edge 400 in the map information. Since the control unit 11 can specify the position of the road shoulder edge 400, it registers the road shoulder edge 400 on the road at the corresponding position in the map information.

The control unit 11 may control the communication unit 17 to transmit map information in which the road edge 400 is registered to the server 100. The server 100 may transmit map information in which the road edge 400 is registered to a navigation device (not shown) of a vehicle (not shown).
Alternatively, the control unit 11 may control the communication unit 17 to transmit information regarding the roadside edge 400 to the server 100. The server 100 may transmit information regarding the road shoulder edge 400 to the navigation device of the vehicle. The navigation device may register information regarding the road shoulder edge 400 in the map information used by the navigation device.
Thereby, the navigation device can use the map information in which the road edge 400 is registered to provide road guidance and guide the vehicle to a position where an emergency stop is possible.

Next, an information processing method according to an embodiment will be described.
FIG. 5 is a flowchart for explaining an information processing method according to an embodiment.

In step ST101, the first acquisition unit 12 acquires point cloud data measured by irradiating a laser onto a surrounding area including the ground surface. The first acquisition unit 12 acquires point cloud data measured in a specific area (road) in which it is desired to acquire a feature 300 on the shoulder of a road, for example.

In step ST102, the second acquisition unit 13 acquires image data obtained by imaging the surrounding area including the ground surface. The second acquisition unit 13 acquires image data of the same specific area (road) where the point cloud data acquired by the first acquisition unit 12 was measured.

In step ST103, the classification unit 14 classifies the ground surface into road surfaces and non-road surfaces based on the point cloud data acquired in step ST101. Here, for example, the classification unit 14 may classify the laser beam reflection points 201a within the same plane as road surfaces, and classify the other reflection points 201b as non-road surfaces.
Note that the classification unit 14 classifies the surrounding area including the ground surface into a road surface and a non-road surface based on the point cloud data obtained in step ST101 and the image data obtained in step ST102. Good too.

In step ST104, the estimation unit 15 estimates the feature 300 based on the reflection point 201b classified as a non-road surface in step ST103.
In this case, the estimation unit 15 selects one processing point among the reflection points 201b as the first point of interest 211, and performs another process different from the first point of interest 211 among the reflection points 201b. (other points of interest 212), select other processing points (other points of interest 212) for which the calculated distance is less than or equal to the first threshold, and connect the selected first point of interest 211 and multiple points of interest. It is also possible to group together other processing points (other points of interest 212).
The estimation unit 15 associates the grouped reflection points 201c (point group) with the shape of the feature 300 set in advance, and when the reflection points 201c (point group) and the shape are associated, It may also be estimated as the terrestrial feature 300 having that shape. For example, when the grouped reflection points 201c (point cloud) are associated with a preset cylindrical shape, the estimation unit 15 determines the size of the reflection points 201c (point cloud) as the feature 300. It is also possible to estimate one of the cushion drum 300a and the rubber pole 300b. For example, the estimating unit 15 may determine which reflection points 201b have variations in the transverse direction (the width direction W of the road) intersecting the extension direction among the plurality of reflection points 201b existing along the extension direction of the road. are grouped and clustered, and when the clustered reflection points 201c (point group) correspond to a preset distribution of feature points of the vegetation 300c, it is estimated as the vegetation 300c as the feature 300. It may also be a thing.

In step ST105, the output control unit 16 outputs the feature 300 estimated in step ST104. For example, the output control unit 16 may display the feature 300 estimated in step ST104 on the display unit 19. Further, for example, the output control unit 16 may store information regarding the feature 300 estimated in step ST104 in the storage unit 18. Further, for example, the output control unit 16 may control the communication unit 17 to transmit the information regarding the feature 300 estimated in step ST104 to the outside (for example, the server 100, etc.).

Note that the control unit 11 may specify the road shoulder edge 400 based on the position of the feature 300 estimated in step ST104. The control unit 11 may register the identified road shoulder edge 400 in the map information. The map information in which the road shoulder edge 400 is registered is used by, for example, a navigation device (not shown).

Next, the effects of this embodiment will be explained.
The information processing device 1 includes a first acquisition unit 12 that acquires point cloud data measured by irradiating the earth surface with a laser, and a first acquisition unit 12 that acquires point cloud data measured by irradiating the earth surface with a laser. The classification unit 14 classifies road surfaces and non-road surfaces, and the point cloud data classified as non-road surfaces by the classification unit 14 is grouped by mutually adjacent reflection points 201b within a predetermined distance, and the grouped reflections are The estimation unit 15 includes an estimation unit 15 that estimates the feature 300 based on the characteristics of the points 201c (point group), and an output unit that outputs the feature 300 estimated by the estimation unit 15.
Thereby, the information processing device 1 can use the estimated feature 300 when reproducing a road map. That is, the information processing device 1 can specify the road shoulder edge 400 based on the estimated position of the feature 300, and can register this road shoulder edge 400 in the road map. Furthermore, the information processing device 1 can register the estimated position of the feature 300 on the road map.
Further, since the information processing device 1 estimates the feature 300 based on data obtained by a mobile mapping system, for example, the information processing device 1 can estimate the feature 300 more quickly and efficiently.

In the information processing device 1, the estimation unit 15 selects one processing point among the reflection points 201b as the first point of interest 211, and the first point of interest 211 is different from the first point of interest 211 among the reflection points 201b. Distances from other processing points (other points of interest 212) are calculated, other processing points (other points of interest 212) for which the calculated distance is less than or equal to the first threshold are selected, and the selected first point of interest 211 and a plurality of other processing points (other points of interest 212) may be grouped together.
Thereby, the information processing device 1 can group mutually adjacent reflection points 201b as a cluster.

In the information processing device 1, the estimation unit 15 does not perform grouping when the number of the selected first point of interest 211 and a plurality of other processing points (other points of interest 212) is equal to or less than a second threshold. You can also use it as
As a result, the information processing device 1 does not group clusters constituting one feature 300 that have a small number of reflection points 201b, so that it is possible to suppress erroneous estimation of the feature 300. .

In the information processing device 1, the estimation unit 15 associates the grouped reflection points 201c (point cloud) with the shape of the feature 300 set in advance, and determines whether the reflection points 201c (point cloud) and the shape are related to each other. If there is a correspondence, it may be estimated as the terrestrial feature 300 having that shape.
As a result, the information processing device 1 can detect the grouped reflection points 201c (points group) can be estimated as the feature 300.

In the information processing device 1, when the grouped reflection points 201c (point group) are associated with a preset cylindrical shape, the estimation unit 15 calculates, according to the size of the reflection points 201c (point group), It is also possible to estimate one of the cushion drum 300a and the rubber pole 300b as the terrestrial feature 300.
Thereby, the information processing device 1 can estimate the cushion drum 300a and the rubber pole 300b as the features 300.

In the information processing device 1, the estimation unit 15 selects reflection points that vary in the transverse direction (road width direction W) that intersects the extension direction, among the plurality of reflection points 201b that exist along the extension direction of the road. 201b are grouped and clustered, and when the clustered reflection points 201c (point group) correspond to a preset distribution of feature points of the vegetation 300c, it is estimated as the vegetation 300c as the feature 300. You can also do it.
Thereby, the information processing device 1 can estimate the vegetation 300c as the feature 300.

The information processing device 1 may include a second acquisition unit 13 that acquires image data obtained by imaging the surrounding area including the ground surface. In this case, the classification unit 14 classifies the ground surface into road surfaces and non-road surfaces based on the image data acquired by the second acquisition unit 13 in addition to the point cloud data acquired by the first acquisition unit 12. You can also do it.
Thereby, the information processing device 1 can classify the point group 201 (reflection points) into either a road surface or a non-road surface using the point cloud data and image data obtained by the mobile mapping system.

In the information processing device 1, the estimation unit 15 acquires the color of the feature 300 based on the image data acquired by the second acquisition unit 13, and determines the color of the feature 300 based on the acquired color of the feature 300. It may also be estimated.
The feature 300 may be given a characteristic color. Therefore, the information processing device 1 can estimate the feature 300 by using color information obtained from the image data.

The information processing method includes a first acquisition step in which a computer acquires point cloud data measured by irradiating a laser onto the earth's surface; A classification step of classifying into road surfaces and non-road surfaces, and point cloud data classified into non-road surfaces by the classification step are grouped into mutually adjacent reflection points 201b within a predetermined distance, and grouped reflection points 201c. An estimation step of estimating the feature 300 based on the features of the (point group) and an output step of outputting the feature 300 estimated by the estimation step are executed.
Thereby, the information processing method can utilize the estimated feature 300 when reproducing a road map. That is, the information processing method can specify the road shoulder edge 400 based on the estimated position of the feature 300, and can register this road shoulder edge 400 in the road map. Furthermore, the information processing method can register the estimated position of the feature 300 on the road map.
Further, since the information processing method estimates the feature 300 based on data obtained by a mobile mapping system, for example, the feature 300 can be estimated more quickly and efficiently.

The information processing program includes a first acquisition function that acquires point cloud data measured by irradiating the ground surface with a laser, and an information processing program that causes the computer to acquire the ground surface based on the point cloud data acquired by the first acquisition function. A classification function that classifies road surfaces and non-road surfaces, and point cloud data that is classified as non-road surfaces by the classification function are grouped by mutually adjacent reflection points 201b within a predetermined distance, and grouped reflection points 201c. An estimation function for estimating a feature 300 based on the characteristics of a point group (point cloud) and an output function for outputting the feature 300 estimated by the estimation function are realized.
Thereby, the information processing program can use the estimated feature 300 when reproducing a road map. That is, the information processing program can specify the road shoulder edge 400 based on the estimated position of the feature 300, and can register this road shoulder edge 400 in the road map. Furthermore, the information processing program can register the estimated position of the feature 300 on the road map.
Further, since the information processing program estimates the feature 300 based on data obtained by a mobile mapping system, for example, the feature 300 can be estimated more quickly and efficiently.

Each part of the information processing device 1 described above may be realized as a function of a computer processing device or the like. That is, the first acquisition unit 12, the second acquisition unit 13, the classification unit 14, the estimation unit 15, and the output control unit 16 of the information processing device 1 have a first acquisition function, a second acquisition function, and Each of these functions may be implemented as a classification function, an estimation function, and an output control function.
The information processing program can cause a computer to realize each of the functions described above. The information processing program may be recorded on a computer-readable non-transitory recording medium such as an external memory or an optical disc.
Further, as described above, each part of the information processing device 1 may be realized by a calculation processing device of a computer or the like. The arithmetic processing device and the like are constituted by, for example, an integrated circuit or the like. Therefore, each part of the information processing device 1 may be realized as a circuit that constitutes an arithmetic processing device or the like. That is, the first acquisition section 12, the second acquisition section 13, the classification section 14, the estimation section 15, and the output control section 16 of the information processing device 1 are a first acquisition circuit, a second acquisition circuit, etc. that constitute an arithmetic processing device of a computer, etc. It may be realized as a circuit, a classification circuit, an estimation circuit, and an output control circuit.
Furthermore, the communication unit 17, storage unit 18, and display unit 19 (output unit) of the information processing device 1 may be realized as a communication function, a storage function, and a display function (output function) including, for example, functions such as an arithmetic processing unit. good. Furthermore, the communication section 17, storage section 18, and display section 19 (output section) of the information processing device 1 are realized as a communication circuit, a storage circuit, and a display circuit (output circuit) by being configured with an integrated circuit, for example. You can. Furthermore, the communication unit 17, storage unit 18, and display unit 19 (output unit) of the information processing device 1 may be configured as a communication device, a storage device, and a display device (output device) by being configured with a plurality of devices, for example. You can.

1 Information processing device 11 Control unit 12 First acquisition unit 13 Second acquisition unit 14 Classification unit 15 Estimation unit 16 Output control unit 17 Communication unit 18 Storage unit 19 Display unit

Claims (8)

a first acquisition unit that acquires point cloud data generated by irradiating a laser onto a surrounding area including the road on which the vehicle is traveling and the shoulder of the road and measuring reflection points reflected by objects;
Based on the point cloud data acquired by the first acquisition unit, a plurality of reflection points that fall within a predetermined distance in the vertical direction are classified into the road surface on which the vehicle runs, and reflection points that are not classified into the road surface are a classification unit that classifies it as a non-road surface;
The point cloud data classified as a non-road surface by the classification unit is grouped by mutually adjacent reflection points within a predetermined distance, and the characteristics of the point cloud are made of a plurality of grouped reflection points as a point group; an estimation unit that estimates a feature corresponding to the point cloud based on the shape of the feature that has been associated in advance ;
an output unit that outputs the feature estimated by the estimation unit ,
When the point group is associated with a preset cylindrical shape, the estimation unit performs cylinder fitting on the point group to obtain the axis direction, height, and radius, and the estimation unit determines that the direction of the axis is on the road surface. and if the height is less than or equal to the threshold for the height, if the radius is smaller than the threshold for distinguishing between a rubber pole and a cushion drum, it is assumed to be a rubber pole; If it is larger than the discrimination threshold, it is assumed to be a cushion drum.
Information processing device. The estimation unit is
Selecting one processing point among the plurality of reflection points as the first point of interest,
Calculate the distance between the first point of interest and another processing point different from the first point of interest among the plurality of reflection points,
selecting another processing point whose calculated distance is less than or equal to the first threshold;
The information processing apparatus according to claim 1, wherein the selected first point of interest and a plurality of other processing points are grouped. The information processing apparatus according to claim 2, wherein the estimation unit does not perform grouping when the number of the selected first point of interest and the plurality of other processing points is less than or equal to a second threshold. The estimation unit performs clustering by grouping reflection points that vary in a transverse direction intersecting the extension direction among a plurality of reflection points existing along the extension direction of the road, and performs clustering. Reflection points are used as a point group, and if they correspond to a preset distribution of feature points of vegetation, they are estimated as vegetation as a feature.
The information processing device according to any one of claims 1 to 3 . comprising a second acquisition unit that acquires image data obtained by imaging the surrounding area ,
The classification unit determines whether there is a feature to be recorded in the image data based on the result of associating the point cloud data acquired by the first acquisition unit with the image data acquired by the second acquisition unit. Classify area as non-road surface
The information processing device according to any one of claims 1 to 4 . The estimation unit acquires the color of the feature based on the image data acquired by the second acquisition unit, and estimates the feature based on the acquired color of the feature.
The information processing device according to claim 5 . The computer is
a first acquisition step of acquiring point cloud data generated by irradiating a laser onto a surrounding area including the road on which the vehicle is traveling and the shoulder of the road and measuring reflection points reflected by objects;
Based on the point cloud data acquired in the first acquisition step, a plurality of reflection points that fall within a predetermined distance in the vertical direction are classified into the road surface on which the vehicle runs, and reflection points that are not classified into the road surface are a classification step of classifying the surface into a non-road surface;
The point cloud data classified as a non-road surface in the classification step is grouped by mutually adjacent reflection points within a predetermined distance, and the characteristics of the point cloud are made of a plurality of grouped reflection points as a point group; an estimation step of estimating a feature corresponding to the point cloud based on the shape of the feature that has been associated in advance ;
an output step of outputting the feature estimated by the estimation step ;
In the estimation step, when the point group is associated with a preset cylindrical shape, the point group is fitted with a cylinder to obtain the direction, height, and radius of the axis, and the direction of the axis is set to the road surface. and if the height is less than or equal to the threshold for the height, if the radius is smaller than the threshold for distinguishing between a rubber pole and a cushion drum, it is assumed to be a rubber pole; If it is larger than the discrimination threshold, it is assumed to be a cushion drum.
Information processing method. to the computer,
a first acquisition function that acquires point cloud data generated by irradiating a laser onto a surrounding area including the road on which the vehicle is traveling and the shoulder of the road and measuring reflection points reflected by objects;
Based on the point cloud data acquired by the first acquisition function, a plurality of reflection points that fall within a predetermined distance in the vertical direction are classified into the road surface on which the vehicle travels, and reflection points that are not classified into the road surface are A classification function for classifying into non-road surfaces,
The point cloud data classified as a non-road surface by the classification function is grouped by mutually adjacent reflection points within a predetermined distance, and the characteristics of the point cloud are made of a plurality of grouped reflection points as a point group; an estimation function that estimates a feature corresponding to the point cloud based on the shape of the feature that has been associated in advance ;
and an output function that outputs the features estimated by the estimation function ,
When a point cloud is associated with a preset cylindrical shape, the estimation function performs cylinder fitting on the point cloud to obtain the direction, height, and radius of the axis, and if the direction of the axis is on the road surface. and if the height is less than or equal to the threshold for the height, if the radius is smaller than the threshold for distinguishing between a rubber pole and a cushion drum, it is presumed to be a rubber pole; If it is larger than the discrimination threshold, it is assumed to be a cushion drum.
Information processing program.

Images