| CPC B60W 40/08 (2013.01) [B60N 2/002 (2013.01); G01S 13/04 (2013.01); G01S 13/89 (2013.01); B60W 2040/0881 (2013.01); B60W 2420/408 (2024.01); B60W 2540/227 (2020.02)] | 15 Claims |
|
1. A method for automatically detecting a seat occupancy state of a seating arrangement having a plurality of seats for which a seat occupancy state is to be determined individually or cumulatively as part of the method, the method comprising:
receiving or generating measurement data, in each case representing an associated radar point cloud for each measurement frame from a plurality of measurement frames, so that the measurement data represents a multiplicity of radar point clouds corresponding to the plurality of measurement frames,
wherein each radar point cloud of the multiplicity of radar point clouds is obtained on the basis of a radar scan of a spatial region surrounding at least some sections of the seating arrangement, which takes place at a measurement time or during a measurement period assigned to the respective measurement frame, and contains radar points,
wherein the plurality of measurement frames comprise a plurality of groups of measurement frames which each comprise one or more measurement frames of the same temporal length, the temporal length of measurement frames of different groups of measurement frames is different, and one corresponding group of radar point clouds is assigned to each of the plurality of groups of measurement frames;
determining a seat occupancy state of the seating arrangement based on an evaluation model, which returns, as a function of at least two groups of radar point clouds, one of a plurality of predefined possible seat occupancy states of the seating arrangement as an evaluation result,
wherein the individual radar points of each radar point cloud are each represented at least by one position of the respective radar point in three-dimensional space;
for each radar point cloud, the set of its radar points is sub-divided by clustering, as a function of the respective spatial position of the radar points in relation to the seats, into a plurality of clusters each containing a subset of the radar points to individually assign to each of the seats one of the clusters located spatially closest to it,
wherein the determination of the seat occupancy state of the seating arrangement comprises an individual determination of a respective individual seat occupancy state for each of the seats as a function of the respective associated clusters of the at least two groups of radar point clouds, to obtain an evaluation result identifying a seat occupancy state of the respective seat;
determining, for each cluster of at least one radar point cloud of that group of the at least two groups of radar point clouds that is assigned to the measurement frame with the smallest temporal length, a number of the radar points contained in the respective cluster, or a quantity dependent on it;
determining whether or not the number of radar points contained in the respective cluster of a single radar point cloud of the particular group of the at least two groups of radar point clouds that is assigned to the measurement frame with the smallest temporal length, or a quantity dependent on that number, or whether or not a mean value of the respective numbers of the radar points contained in respective clusters of multiple radar point clouds, spatially corresponding to each other, of the particular group of the at least two groups of radar point clouds that is assigned to the measurement frame with the smallest temporal length, or a quantity dependent on that number, is less than a first predefined threshold value;
updating a stored seat occupancy state based on the evaluation result only if, for each cluster of the individual radar point cloud of the particular group of the at least two groups of radar point clouds that is assigned to the measurement frame with the smallest temporal length, the number of radar points or the quantity dependent on it is less than the first predefined threshold value, or if all the mean values of the respective numbers of the radar points in respective clusters of multiple radar point clouds, spatially corresponding to each other, of the particular group of the at least two groups of radar point clouds that is assigned to the measurement frame with the smallest temporal length, or the quantity dependent on that value, is less than the first predefined threshold; and
outputting information defined according to the evaluation result if the stored seat occupancy state has been updated.
|