Method for analyzing at least one object in the environment of a vehicle sensor device

Abstract

The present invention relates to a method for analyzing at least one object (23) in the environment (5) of a sensor device (2) for a vehicle (1). The method includes: providing sensor information (12) describing at least one object (23) by at least one measurement point (11) located at a first radial distance (r1) from the sensor device (2) (S2); determining artificial sensor information (13) describing at least one artificial point (14) in the environment (5) (S4), wherein the artificial point (14) is located at a second radial distance (r2) from the sensor device (2) that is greater than the first radial distance (r1) by a predetermined distance value (Δr); and analyzing at least one object (23) (S6) by applying an analysis algorithm (21) to both the provided sensor information (12) and the determined artificial sensor information (13).

Description

Technical Field

[0001] The present invention relates to a method for analyzing at least one object in the environment of a vehicle sensor device. The present invention further relates to a vehicle, a computing device for a vehicle, and a computer program product for executing such a method.

Background Art

[0002] A vehicle can be equipped with at least one sensor device for capturing sensor information describing the environment of the vehicle. The sensor device may be a radar device, a lidar device, and / or a camera mounted on the vehicle. In the case of at least a radar device and / or a lidar device as the sensor device, the captured sensor information can be a point cloud of a plurality of measurement points captured by each sensor device. However, when an object in the environment is far from the sensor device, for example, more than 50 meters away, the local density of the measurement points captured by each sensor device can be lower compared to the local density of the measurement points of an object closer to the sensor device. Therefore, the sensor device acquires sparse sensor information for distant objects. This can be disadvantageous for the analysis of sensor information, especially when the analysis is performed for object detection and / or semantic segmentation.

Summary of the Invention

Problems to be Solved by the Invention

[0003] An object of the present invention is to improve the measurement point density of the measurement points provided by the sensor device.

Means for Solving the Problems

[0004] The subject matter of the independent claims solves this object.

[0005] A first aspect of the present invention relates to a method for analyzing at least one object in the environment of a vehicle sensor device. Preferably, the sensor device is mounted on a vehicle. The vehicle may comprise a plurality of sensor devices, each configured to capture sensor information describing the environment of each sensor device. The environment is generally defined by the coverage area of ​​the sensor devices.

[0006] This method includes providing sensor information. The sensor information describes at least one object by at least one measurement point located at a first radial distance from the sensor device. The at least one object described by the sensor information is an object in the environment of the sensor device. The at least one measurement point is described, for example, by the coordinates of a point. In particular, the coordinates are given relative to the sensor device. The coordinates consist of at least a value representing the radial distance from the sensor device and / or a reference point of the sensor device. The radial distance may alternatively be called the radius of the measurement point or radial coordinates. Generally, the sensor information describes at least one object by a plurality of measurement points located at different first radial distances from the sensor device. If a plurality of objects exist in the environment of the sensor device, the sensor information can describe a plurality of objects, each object preferably described by a plurality of measurement points. The sensor information may be provided to the vehicle's computing device and / or server, backend and / or external computing device such as a cloud server. The sensor information may be described by sensor data.

[0007] This method includes determining artificial sensor information. The artificial sensor information describes at least one artificial point in the environment. The artificial point is located at a second radial distance from the sensor device. The second radial distance is greater than the first radial distance by a predetermined distance value. Therefore, the artificial sensor information describes a simulated point, not an actual point in the environment. The artificial point is not captured by the sensor device. Therefore, sensor information captured by the sensor device does not describe at least one artificial point. Alternatively or additionally, the artificial sensor information may be called synthesized or simulated sensor information. The predetermined distance value may be, for example, 1 millimeter, 2 millimeters, 3 millimeters, 5 millimeters, 8 millimeters, 1 centimeter, 1.5 centimeters, 2 centimeters, 3 centimeters, or in particular 5 centimeters. The distance value may be any value between the above values.

[0008] Since the second radial distance is greater than the first radial distance, the artificial point is located behind the measurement point from the viewpoint of the sensor device. Therefore, the artificial point is a point that may not be detectable by the sensor device because it is located inside the object. Assume that the measurement point is located on the surface of the object. In this case, the artificial point cannot overlap with any measurement point unless, for example, the light rays emitted by the sensor device can at least partially penetrate the surface of the object, are behind the surface of the object, and are reflected by a part of the object located at the second radial distance.

[0009] This method further includes analyzing at least one object by applying an analysis algorithm to both the provided sensor information and the determined artificial sensor information. The analysis may include, for example, the classification of objects in the environment. The analysis algorithm includes at least one rule and / or condition for analyzing the object. The analysis algorithm is performed considering not only the measured sensor data, which represents the provided sensor information, but also the artificially created data, which represents the determined artificial sensor information. Since each measurement point describing the object is at least duplicated by considering at least one artificial point, the number of points to which the analysis algorithm is applied is at least twice the number of measurement points described by the provided sensor information. If there are multiple artificial points selected for each measurement point, it is possible to increase the total number of points considered for analyzing the object by a predetermined coefficient, the coefficient depending on the number of artificial points per measurement point. As a result, the point cloud describing the object increases while the structure and / or contour of the object is preserved. The structure and / or contour is preserved by the position of at least one artificial point for each measurement point in the radial direction. Thus, the local density of points used to analyze at least one object increases compared to the local density of measurement points. Therefore, the density of measurement points provided by the sensor device increases.

[0010] One embodiment involves providing sensor information and determining artificial sensor information, each describing at least one point using spherical coordinates. The at least one measurement point and the at least one artificial point are positioned at a common polar angle and azimuth angle. That is, for example, if there is exactly one measurement point that determines exactly one artificial point, then these two points have different radial distances because the first radial distance is not equal to the second radial distance. However, they have the same polar angle and the same azimuth angle. Therefore, from the viewpoint of the sensor device, both points are located behind each other in radial distance, but are not adjacent to each other in a direction perpendicular to the radial direction due to the same polar angle and azimuth angle.

[0011] If multiple measurement points exist and at least one artificial point is determined for each, each measurement point and its associated or linked artificial point are located at their respective common polar angle and azimuth angle. In other words, if there are multiple measurement points, they may have different polar angles and azimuth angles. However, each artificial point of multiple measurement points will coincide in both polar angle and azimuth angle, but will have different radial distances. That is, sensor information describing at least one object by at least one measurement point uses spherical coordinates so that at least one measurement point is described by a first radial distance, polar angle, and azimuth angle. Artificial sensor information also uses spherical coordinates to describe at least one artificial point so that the artificial point is described by a second radial distance, polar angle, and azimuth angle. Therefore, there are no first and second polar angles and / or first and second azimuth angles, and there is only one common angle between the polar angle and azimuth angle. Therefore, at least one artificial point does not affect, for example, the shape and / or size of the object, but only the density of measurement points on the surface of the object. This is achieved by keeping the polar angle and azimuth angle of each measurement and artificial point constant.

[0012] A further embodiment comprises a measurement point being part of at least one three-dimensional point cloud captured by a sensor device. Thus, the sensor device is configured to detect a three-dimensional object. Since each measurement point represents a single point on the surface of the object, the three-dimensional point cloud of individual measurement points represents the surface of the object. The three-dimensional point cloud is general raw data provided by the vehicle's sensor device. Therefore, the method can be based on general sensor information provided by the vehicle.

[0013] In a further embodiment, the method includes projecting the provided sensor information and determined artificial sensor information onto a two-dimensional plane before applying the analysis algorithm. That is, the three-dimensional point cloud is processed first to create a two-dimensional arrangement of points. The two-dimensional arrangement of points, which represents a two-dimensional plane of measured points, is sometimes called a two-dimensional point cloud. Instead of analyzing a three-dimensional view of an object, the three-dimensional point cloud is converted into a two-dimensional view of the object, such as a still image and / or moving image of the points. For example, it is particularly reasonable to move both the sensor information and artificial sensor information from three dimensions to two dimensions in order to apply a common analysis algorithm developed for analyzing two-dimensional sensor information.

[0014] Furthermore, one embodiment includes projected sensor information and projected artificial sensor information describing the environment from a bird's-eye view and / or a side view. This is particularly reasonable when the sensor device is a component of a vehicle. Generally, multiple sensor devices are arranged or mounted within a vehicle so that the sensor information can describe the entire environment, for example, a 360-degree view of the vehicle's environment. In such a scenario, the viewpoint of the measurement point in the two-dimensional plane is often a top view of the environment. The top view is a bird's-eye view. Alternatively, it may be called a top view. However, if only sensor information from one side of the vehicle is provided, for example, the plane formed by the height and length of the vehicle can be selected as the two-dimensional plane. As a result, a side view is generated. Alternatively, it may be called a side view of the environment. The two-dimensional plane of the side view is preferably positioned perpendicular to the two-dimensional plane of the bird's-eye view. Finally, a particularly useful view of the environment is created and can be used to analyze objects.

[0015] A preferred embodiment includes the artificial sensor information describing a first artificial point and at least one second artificial point. Preferably, the artificial sensor information describes a plurality of second artificial points. The second radial distance of the first artificial point is greater than the first radial distance by a predetermined distance value. Furthermore, the second radial distance of the first artificial point is less than the second radial distance of at least one second artificial point by a predetermined distance value. In other words, when viewed radially, the measurement point is placed first, followed by the first artificial point, followed by at least one second artificial point. Thus, it is possible to place at least two artificial points radially behind the measurement point. It is preferable that all of these artificial points have the same polar angle and azimuth angle as the measurement point. As a result, the point density at the location of each measurement point can be greatly increased. This particularly explains why the contours of objects appear with higher contrast when artificial sensor information is determined and considered.

[0016] Another embodiment involves artificial sensor information describing a plurality of second artificial points. The second radial distance between the plurality of second artificial points is such that they are spatially separated by a predetermined distance value in the radial direction. Thus, the distance between two radially adjacent second artificial points is equal to the predetermined distance value. Therefore, all artificial points corresponding to one measurement point are equidistant from each other in the radial direction. Thus, since they are all located at a predetermined distance from each other, adding new artificial points is particularly easy.

[0017] Another embodiment includes the distribution of artificial points over a predetermined radial distance range. The radial distance range is from a first radial distance as a minimum radial distance to a predetermined maximum radial distance. The radial distance range is, for example, 1 centimeter, 3 centimeters, 5 centimeters, 10 centimeters, 15 centimeters, 20 centimeters, 30 centimeters, 50 centimeters, or in particular 1 meter. Depending on the predetermined distance value, the number of artificial points required to fill the entire predetermined radial distance range can be determined. Thus, it is possible to set a radial distance range in which at least one artificial point can be placed radially behind the measurement point. Therefore, by changing the radial distance range and / or the predetermined distance value, it is possible to obtain different point cloud densities.

[0018] According to a preferred embodiment, artificial sensor information is determined only for measurement points where the first radial distance is greater than a predetermined minimum value. In other words, the method consists of determining artificial sensor information only for measurement points located further from the sensor device as the first radial distance greater than a predetermined minimum value. The predetermined minimum value may be, for example, 10 meters, 20 meters, 30 meters, 40 meters, 50 meters, 60 meters, 70 meters, 80 meters, 90 meters, or especially 100 meters. The minimum value may be any value among the enumerated values. Therefore, it is possible not to determine artificial sensor information for objects located at a first radial distance closer to the device than the distance corresponding to the predetermined minimum value, or for objects located at the distance corresponding to the predetermined minimum value. However, if an object is located further than the distance corresponding to the predetermined minimum value, it is assumed that artificial sensor information is determined because particularly sparse sensor information is provided and is particularly captured by the sensor device. This reduces the required computation time because artificial sensor information is determined only when sparse sensor information is expected.

[0019] Alternatively or additionally, for measurement points where the first radial distance is less than or equal to a predetermined minimum value, the number of artificial points may be reduced compared to the number of artificial points determined for measurement points where the first radial distance is greater than the predetermined minimum value. However, the number of artificial points may be greater than zero.

[0020] According to another embodiment, the method includes capturing sensor information by a radar device, a LiDAR device, and / or a time-of-flight camera. Generally, the sensor information describes the position of at least one point of an object relative to the sensor device. Therefore, the sensor information is preferably information describing the distance between the object and the radar device. The captured sensor information is provided as sensor information for determining artificial sensor information. Therefore, there are versatile sensor devices that can provide sensor information.

[0021] The sensor device is preferably mounted on the vehicle, for example, on the vehicle's bumper and / or chassis. The sensor device may be located in the front, rear, and / or lateral regions of the vehicle.

[0022] Another embodiment involves converting captured raw sensor information from Cartesian coordinates to spherical coordinates and providing the converted sensor information as sensor information. Therefore, if the sensor device captures its data in Cartesian coordinates, an additional conversion step is required to determine the respective coordinates in spherical coordinates for each measurement point. Spherical coordinates define the radial position. The position of each measurement point is called its respective first radial distance. It is possible to perform an inverse conversion from spherical coordinates to Cartesian coordinates before applying an analysis algorithm to the sensor information and artificial sensor information. General conversion techniques for coordinate transformations between these two coordinate systems can be applied to the conversion between Cartesian and spherical coordinates. Therefore, this method does not require the sensor device to provide sensor information in spherical coordinates.

[0023] Another embodiment includes an analysis algorithm that performs object detection and / or semantic segmentation. The analysis algorithm may, in particular, include a convolutional neural network. The analysis algorithm is configured to, for example, detect, identify, and / or classify objects. By the convolutional neural network, for example, if the convolutional neural network is trained to classify objects, it is possible to perform object classification. Semantic segmentation means that each pixel, and therefore each measurement point and artificial point, is assigned to a specific object class. It is possible to determine object information by applying the analysis algorithm to the provided sensor information and the determined artificial sensor information. The object information can describe the results of the analysis algorithm, for example, the object and / or the class of the object. The object information may be provided to the functions of the vehicle, for example, the driver assistance system. Thus, the method can provide information necessary for the functions of the vehicle.

[0024] Another aspect of the present invention relates to a vehicle. The vehicle is configured to carry out the method described above. The vehicle corresponds to the first vehicle. The vehicle is an automobile, particularly a passenger car, truck, bus and / or motorcycle. The vehicle carries out the method. The vehicle preferably includes a sensor device, e.g., a radar device, a LiDAR device and / or a time-of-flight camera. Preferably, the vehicle includes a computing device, the computing device determines artificial sensor information and applies an analysis algorithm to the provided sensor information and the determined artificial sensor information. Thus, the sensor device of the vehicle provides sensor information to the computing device.

[0025] A further aspect of the present invention relates to a computing device for a vehicle. The computing device is configured to execute the above-described method. The computing device executes the described method, particularly at least one or a combination of embodiments of the described method. The computing device comprises a processor device. The processor device can comprise at least one microprocessor and / or at least one microcontroller and / or at least one FPGA (Field Programmable Gate Array) and / or at least one DSP (Digital Signal Processor). Further, the processor device can include program code. Alternatively, the program code may be referred to as a computer program product or a computer program. The program code can be stored in the data memory of the processor device.

[0026] Another aspect of the present invention relates to a computer program product. A computer program product is a computer program. The computer program product includes instructions that cause a computer, such as a computing device, to execute the method of the present invention when the program is executed by the computer.

[0027] Therefore, the embodiments described in connection with the present method are applicable, as far as possible, individually and in combination with each other, to the vehicle, the computing device, and / or the computer program product of the present invention. The present invention includes combinations of the described embodiments.

Brief Description of the Drawings

[0028] [Figure 1] It is a schematic diagram of a vehicle provided with a plurality of sensor devices. [Figure 2] It is a schematic diagram of a method for analyzing at least one object in an environment of a vehicle sensor device. [Figure 3] It is a schematic diagram of sensor information and artificial sensor information.

Modes for Carrying Out the Invention

[0029] Figure 1 shows a vehicle 1 equipped with multiple sensor devices 2. Here, the sensor devices 2 include multiple radar devices 3 and lidar devices 4. Alternatively or additionally, the sensor devices 2 may include time-of-flight cameras (not shown here). Here, the radar devices 3 and lidar devices 4 are located in the front, rear, and lateral regions of the vehicle 1. The vehicle 1 may have more or fewer radar devices 3 and / or lidar devices 4. The sketched sensor devices 2 may be located in different locations within the vehicle 1. Preferably, the radar devices 3 and lidar devices 4 are located, for example, in the bumper and / or chassis of the vehicle 1. Two radar devices located on opposite sides in the y-direction are located, for example, in the doors of the vehicle 1. Each sensor device 2 is configured to capture data describing the environment 5 of the vehicle 1. The environment 5 is preferably defined by the coverage area of ​​each sensor device 2.

[0030] Vehicle 1 may include a computing device 6. Alternatively, the computing device 6 may be called a control unit or control device of Vehicle 1. The computing device 6 is configured, for example, to perform calculations. Thus, it can perform steps of a method for analyzing the environment 5 of the sensor device 2, and therefore at least one object 23 (see reference numeral 23 in Figure 3) in the environment 5 of Vehicle 1.

[0031] Figure 2 shows the steps of a method for analyzing at least one object 23 in the environment 5 of sensor device 2. In step S1, the method may include capturing sensor information 12 by radar device 3, lidar device 4, and / or time-of-flight camera of vehicle 1. Sensor device 2 captures sensor information 12. The sensor information 12 describes at least one object 23 in the environment 5 of sensor device 2 by at least one measurement point 11.

[0032] Step S2 includes providing sensor information 12 that describes at least one object 23 by at least one measurement point 11. The at least one measurement point 11 is located at a first radial distance r1, where r1 is the distance to the sensor device 2 or another reference point. Generally, the measurement point 11 is described in spherical coordinates. Thus, the measurement point 11 is described by the first radial distance r1, the polar angle θ, and the azimuth angle φ. The sensor information 12 may be provided to the computing device 6.

[0033] When sensor device 2 captures sensor information 12 in Cartesian coordinates, raw sensor information 10 is captured by sensor device 2. Then, the captured raw sensor information 10 is converted to spherical coordinates in step S3. The converted sensor information is then provided as sensor information 12.

[0034] Step S4 includes determining artificial sensor information 13 that describes at least one artificial point 14 in the environment 5. The artificial point 14 is located at a second radial distance r2 with respect to the sensor device 2. The second radial distance r2 is greater than the first radial distance r1 by a predetermined distance value Δr. More specifically, the artificial point 14 is described by the same polar angle θ and the same azimuth angle φ as the measurement point 11. That is, when the measurement point 11 is compared to the artificial point 14, only the radial distances r1 and r2 differ. In other words, the provided sensor information 12 and the determined artificial sensor information 13 describe at least one point 11, 14 respectively using spherical coordinates, but at least one measurement point 11 and at least one artificial point 14 are located at a common polar angle θ and a common azimuth angle φ.

[0035] The artificial sensor information 13 may describe a first artificial point 15 and at least one second artificial point 16. Here, three second artificial points 16 are described. More or fewer second artificial points 16 are possible. The second radial distance r2 of the first artificial point 15 is greater than the first radial distance r1 of the measurement point 11 by a predetermined distance value Δr. The second radial distance r2 of the first artificial point 15 is less than the second radial distance r2 of at least one second artificial point 16 by a predetermined distance value Δr. If there are multiple second artificial points 16, the second radial distances r2 of the multiple second artificial points 16 are each spatially separated by a predetermined distance value Δr in the radial direction. In total, the artificial points 14 can be distributed over a predetermined radial distance range R. The radial distance range R is from a first radial distance r1 as the minimum radial distance 17 to a predetermined maximum radial distance 18. Here, the range R of the radial distance is four times the predetermined distance value Δr.

[0036] This method may include determining artificial sensor information 13 only for measurement points 11 where the first radial distance r1 is greater than a predetermined minimum value r0. The minimum value r0 may be, for example, 60 meters or 80 meters relative to the position of the sensor device 2 and / or vehicle 1.

[0037] The measurement point 11 may be part of at least one three-dimensional point cloud 19 that can be captured by the sensor device 2. In step S5, the provided sensor information 12 and the determined artificial sensor information 13 can be projected onto a two-dimensional plane 20. That is, the projected sensor information 12 and artificial sensor information 13 form a two-dimensional set of points 11 and 14. The projected sensor information 12 and projected artificial sensor information 13 can describe the environment 5 from a bird's-eye view and / or a side view.

[0038] Step S6 includes analyzing at least one object 23 by applying an analysis algorithm 21 to both the provided sensor information 12 and the determined artificial sensor information 13. The analysis algorithm 21 can perform object detection and / or semantic segmentation. The analysis algorithm 21 can include, for example, a convolutional neural network to classify the object 23. The analysis results obtained by applying the analysis algorithm 21 are included in the object information 22. The object information 22 can describe the object 23, in particular the class of the object 23.

[0039] Figure 3 shows an example of sensor information 12 and corresponding artificial sensor information 13. Three other vehicles 1 are located in the environment 5 of vehicle 1. The other three vehicles 1 are objects 23. More objects 23 and / or other objects 23 are possible in the environment. However, as shown by the respective thin lines in Figure 3, only a few measurement points 11 are captured by the sensor device 2 on each contour, and therefore surface, of object 23. By adding multiple artificial points 14 for each of the measurement points 11, a denser contour of object 23 is artificially created, as shown by the respective relatively thick lines in Figure 3. As a result, the analysis results when the analysis algorithm 21 is applied to both sensor information 12 and artificial sensor information 13 may be better than when it is applied to sensor information 12 only.

[0040] In summary, the invention describes the extrapolation of distance-azimuth data for augmenting sensor data in a distance sensor. The invention relates to sensor data from a radar sensor or a lidar sensor, i.e., sensor data from a radar device 3 and / or a lidar device 4 that generate respective point clouds 19 as measurement results. The sensor data consists of provided sensor information 12. The point clouds 19 are projected onto a two-dimensional plane 20.

[0041] Due to the low density of the point cloud 19, the classifier (analysis algorithm 21) has a problem classifying the object 23. The idea is to increase the point cloud density without adding noise related to the shape of the object 23. This is done by adding additional artificial points 14 distributed radially r1, r2 for each measurement point 11. This method preserves the contour and adds very little noise.

[0042] Regarding the conversion to spherical coordinates, each three-dimensional point (x, y, z) in the point cloud 19 generated by the sensor device 2 can be expressed in spherical coordinates as (r, θ, φ), where r is the range or radial distance, θ is the elevation angle (polar angle), and φ is the azimuth angle.

number

number

number

[0043] By maintaining θ and φ, the radial distance r is increased by a small amount Δr, resulting in new points within object 23 as if a light ray had passed through it. This can help to make the point cloud 19 denser while maintaining the structure and contours of object 23 in the scene.

[0044] The proposed method does not use a learning-based convolutional neural network, but rather simply applies a mathematical technique to extrapolate the light rays connecting the sensor's origin and observation points. Therefore, the potential for error is significantly lower compared to methods based on convolutional neural networks. Furthermore, while training a convolutional neural network requires the expressed ground truth data, this proposed method does not. In addition, the proposed method can be easily adjusted to augment only sections of the input point cloud 19, for example, to reinforce only the range beyond 80 meters. That is, the minimum value r0 can be considered and set to, for example, 80 meters. This method is applicable to all types of distance sensors and is not limited to lidar.

Claims

1. A method for analyzing at least one object (23) in the environment (5) of a sensor device (2) for a vehicle (1), The first radial distance (r) relative to the sensor device (2) 1 Step (S2) provides sensor information (12) that describes the at least one object (23) by at least one measurement point (11) located at ), Step (S4) of determining artificial sensor information (13) describing at least one artificial point (14) in the environment (5), wherein the artificial point (14) is the first radial distance (r 1 The second radial distance (r) to the sensor device (2) is greater than a predetermined distance value (Δr) than the first radial distance (r) 2 ) is located at step (S4), Step (S6) of analyzing the at least one object (23) by applying the analysis algorithm (21) to both the provided sensor information (12) and the determined artificial sensor information (13) Methods that include...

2. The method according to claim 1, wherein the provided sensor information (12) and the determined artificial sensor information (13) describe each of the at least one point (11, 14) using spherical coordinates, and the at least one measurement point (11) and the at least one artificial point (14) are located at a common polar angle (θ) and azimuth angle (φ).

3. The method according to any one of claims 1 to 2, wherein the measurement point (11) is part of at least one three-dimensional point cloud (19) captured by the sensor device (2).

4. The method according to claim 3, comprising the step (S5) of projecting the provided sensor information (12) and the determined artificial sensor information (13) onto a two-dimensional plane (20) before applying the analysis algorithm (21).

5. The method according to claim 4, wherein the projected sensor information (12) and artificial sensor information (13) describe the environment (5) from a bird's-eye view and / or a side view.

6. The artificial sensor information (13) describes a first artificial point (15) and at least one second artificial point (16), and the second radial distance (r 2 ) is the first radial distance (r 1 The distance is greater than the predetermined distance value (Δr) of the at least one second artificial point (16) in the second radial distance (r 2 The method according to any one of claims 1 to 5, wherein the distance is smaller than the predetermined distance value (Δr) of the specified distance.

7. The artificial sensor information (13) describes a plurality of second artificial points (16), and the second radial distance (r 2 The method according to claim 6, wherein each of them is spatially separated from the others in the radial direction by a predetermined distance value (Δr).

8. The artificial point (14) is the first radial distance (r) as the minimum radial distance (17). 1 The method according to claim 7, wherein the distribution extends over a predetermined radial distance range (R) from ) to a predetermined maximum radial distance (18).

9. The step of determining the artificial sensor information (13) only for the measurement points (11) where the first radial distance (r 1 ) is greater than a predetermined minimum value (r 0 ), the method according to any one of claims 1 to 8.

10. The method according to any one of claims 1 to 9, comprising the step (S1) of capturing the sensor information (12) by a radar device (3), a lidar device (4), and / or a time-of-flight camera.

11. The method according to claim 10, comprising the steps of: converting captured raw sensor information (10) from Cartesian coordinates to spherical coordinates (S3); and providing the converted sensor information as the sensor information (12).

12. The method according to any one of claims 1 to 11, wherein the analysis algorithm (21) performs object detection and / or semantic segmentation, and in particular comprises a convolutional neural network.

13. A vehicle (1) configured to perform the method described in any one of claims 1 to 12.

14. A computing device (6) for a vehicle (1) configured to perform the method described in any one of claims 1 to 12.

15. A computer program product comprising instructions, wherein when the program is executed by a computer, the computer causes the computer to perform the method described in any one of claims 1 to 12.

Images