Method for classifying measuring points of a point cloud
A method for classifying measuring points of a point cloud ascertained by at least one sensor, in particular, a point cloud ascertained from a LIDAR sensor, a radar sensor and/or a camera sensor, via a control unit. Local surface vectors to adjacent measuring points are ascertained for each measuring point of the point cloud. For each local surface vector, respectively one angle is calculated between the local surface vectors with respect to a gravity vector. A maximal surface vector having a maximal angle with respect to the gravity vector and a standardized surface vector are ascertained for each measuring point of the point cloud based on the calculated angles. Each measuring point of the point cloud includes a standardized surface vector and/or includes a maximal surface vector having an angle with respect to the gravity vector above a limiting value being classified as a non-ground point.
1. A method for classifying measuring points of a point cloud ascertained by at least one sensor, the method comprising:
ascertaining the point cloud, using a sensor, via a control unit, the sensor including a LIDAR sensor, and/or a radar sensor and/or a camera sensor;
ascertaining local surface vectors to adjacent measuring points for each measuring point of the point cloud;
calculating, for each of the local surface vectors, respectively an angle between the local surface vectors with respect to a gravity vector;
ascertaining a maximal surface vector having a maximal angle with respect to the gravity vector and a standardized surface vector, for each of the measuring points of the point cloud, based on the calculated angles; and
classifying each of the measuring points of the point cloud including a standardized surface vector and/or including a maximal surface vector having an angle with respect to the gravity vector above a limiting value, as a non-ground point, wherein:
a height value is compared with a height of the sensor above a ground for each non-classified measuring point of the point cloud, each non-classified measuring point of the point cloud being classified as a ground point when its height value matches the height of sensor above the ground, and
the measuring points of the point cloud classified as ground points are ascertained using at least one non-classified, adjacent measuring point, and a region growing method is applied.
2. The method as recited in claim 1 , wherein non-classified, adjacent measuring points are ascertained from the measuring points classified as non-ground points, non-classified, adjacent measuring points of the measuring points classified as non-ground points having an identical azimuth angle and a higher or identical elevation angle being classified as non-ground points.
3. The method as recited in claim 1 , wherein the measuring points of the point cloud are at least buffered in a memory unit in a structured form including a plurality of rows and columns.
4. A control unit configured to classify measuring points of a point cloud ascertained by at least one sensor, the control unit configured to:
ascertain the point cloud using a sensor, the sensor including a LIDAR sensor, and/or a radar sensor and/or a camera sensor;
ascertain local surface vectors to adjacent measuring points for each measuring point of the point cloud;
calculate, for each of the local surface vectors, respectively an angle between the local surface vectors with respect to a gravity vector;
ascertain a maximal surface vector having a maximal angle with respect to the gravity vector and a standardized surface vector, for each of the measuring points of the point cloud, based on the calculated angles; and
classify each of the measuring points of the point cloud including a standardized surface vector and/or including a maximal surface vector having an angle with respect to the gravity vector above a limiting value, as a non-ground point, wherein:
a height value is compared with a height of the sensor above a ground for each non-classified measuring point of the point cloud, each non-classified measuring point of the point cloud being classified as a ground point when its height value matches the height of sensor above the ground, and
the measuring points of the point cloud classified as ground points are ascertained using at least one non-classified, adjacent measuring point, and a region growing method is applied.
5. A non-transitory machine-readable memory medium on which is stored a computer program for classifying measuring points of a point cloud ascertained by at least one sensor, the computer program, when executed by a computer, causing the computer to perform the following steps:
ascertaining the point cloud using a sensor, the sensor including a LIDAR sensor, and/or a radar sensor and/or a camera sensor;
ascertaining local surface vectors to adjacent measuring points for each measuring point of the point cloud;
calculating, for each of the local surface vectors, respectively an angle between the local surface vectors with respect to a gravity vector;
ascertaining, a maximal surface vector having a maximal angle with respect to the gravity vector and a standardized surface vector, for each of the measuring points of the point cloud, based on the calculated angles; and
classifying each of the measuring points of the point cloud including a standardized surface vector and/or including a maximal surface vector having an angle with respect to the gravity vector above a limiting value, as a non-ground point, wherein:
a height value is compared with a height of the sensor above a ground for each non-classified measuring point of the point cloud, each non-classified measuring point of the point cloud being classified as a ground point when its height value matches the height of sensor above the ground, and
the measuring points of the point cloud classified as ground points are ascertained using at least one non-classified, adjacent measuring point, and a region growing method is applied.