Foreground extraction using surface fitting
AssigneeMotional AD LLC
InventorsAbbas Shikari, Jiaxin Li, Thomas Koelbaek Jespersen
Life of this patent
Estimating the term…
Abstract
Techniques are provided for foreground extraction from a point cloud (e.g., a LiDAR point cloud) using surface fitting. In an embodiment, one or more processors of a vehicle can receive point cloud data from one or more vehicle sensors. The one or more processors can identify points in the point cloud data as foreground points or ground points using a spatial Kalman filter to capture changes in the terrain. A route or trajectory in a driving area for the vehicle can be generated using the identified foreground points and ground points. A vehicle controller can control the vehicle while the vehicle is traveling on the route or trajectory in the driving area.
Claims21
1-30. (canceled)
A computer-implemented method comprising:
- receiving, using one or more processors of a vehicle, data comprising multi-dimensional points from one or more sensors of the vehicle;
- transforming, using the one or more processors, the data into a grid comprising a plurality of cells, each cell comprising one or more points;
- predicting a height and slope of terrain at each point in each cell using a spatial Kalman filter (SKF);
- performing an innovation-based outlier rejection calculation at each point, and
- performing an SKF update to identify foreground points and ground points;
- generating, using one or more processors, a trajectory in a driving area for the vehicle using the identified foreground points and ground points;
- and
- controlling, using a vehicle controller, the vehicle while the vehicle is traveling on the trajectory in the driving area.
A foreground extraction system for a vehicle, the foreground extraction system comprising:
- one or more sensors;
- one or more processors of the vehicle;
- memory storing instructions that when executed by the one or more processors, cause the one or more processors to perform operations comprising:
- receiving, using one or more processors of a vehicle, data comprising multi-dimensional points from one or more sensors of the vehicle;
- transforming , using the one or more processors, the data into a grid comprising a plurality of cells, each cell comprising one or more points;
- predicting a height and slope of terrain at each point in each cell using a spatial Kalman filter (SKF);
- performing an innovation-based outlier rejection calculation at each point;
- performing an SKF update to identify foreground points and ground points;
- generating, using one or more processors, a trajectory in a driving area for the vehicle using the identified foreground points and ground points;
- and
- controlling, using a vehicle controller, the vehicle while the vehicle is traveling on the trajectory in the driving area.
A non-transitory computer program product storing instructions that, when executed by at least one programmable processor of a vehicle, cause the at least one programmable processor to perform operations comprising:
- receiving, using one or more processors of a vehicle, data comprising multi-dimensional points from one or more sensors of the vehicle;
- transforming, using the one or more processors, the data into a grid comprising a plurality of cells, each cell comprising one or more points;
- predicting a height and slope of terrain at each point in each cell using a spatial Kalman filter (SKF);
- performing an innovation-based outlier rejection calculation at each point;
- performing an SKF update to identify foreground points and ground points;
- generating, using one or more processors, a trajectory in a driving area for the vehicle using the identified foreground points and ground points;
- and
- controlling, using a vehicle controller, the vehicle while the vehicle is traveling on the trajectory in the driving area.
Dependencies are inferred from the claim text.