Hybrid evaluation of radar data for classifying objects

A non-transitory machine-readable data medium on which is stored a computer program for classifying objects based on measured data recorded by at least one radar sensor, the computer program, when executed by one or more computers, causing the one or more computers to perform the following steps:

• providing a frequency spectrum of time-dependent measured data of the radar sensor;
• ascertaining, from the frequency spectrum, locations from which reflected radar radiation has reached the radar sensor;
• ascertaining at least one group of the locations belonging to one and the same object;
• ascertaining, for each location in the group of the locations, a portion of the frequency spectrum that corresponds to the radar radiation reflected from the location;
• aggregating and feeding to a classier all of the portions for the object;
• and
• assigning the object, by the classifier, to one or multiple classes of a predefined classification.

A computer configured to classify objects based on measured data recorded by at least one radar sensor, the computer configured to:

• provide a frequency spectrum of time-dependent measured data of the radar sensor;
• ascertain, from the frequency spectrum, locations from which reflected radar radiation has reached the radar sensor;
• ascertain at least one group of the locations belonging to one and the same object;
• ascertain, for each location in the group of the locations, a portion of the frequency spectrum that corresponds to the radar radiation reflected from the location;
• aggregate and feed to a classier all of the portions for the object;
• and
• assign the object, by the classifier, to one or multiple classes of a predefined classification.