| CPC G01S 7/412 (2013.01) [G06F 21/44 (2013.01)] | 22 Claims |
|
1. A processor-implemented radar data recognition method, the method comprising:
generating a plurality of pieces of input data, with respectively different dimension configurations, based on radar data, measured using sensors, of an object; and
performing a recognition operation of the object to output a recognition result of the object based on a plurality of pieces of extracted feature data extracted from the generated plurality of pieces of input data using a plurality of feature extraction models, respectively corresponding to the respectively different dimension configurations, included in a recognition model,
wherein the generating of the plurality of pieces of input data comprises generating, based on the radar data:
first input data of the plurality of pieces of input data comprising a first input map with an angle dimension and a range-velocity dimension for each time frame channel of the first input data;
second input data of the plurality of pieces of input data comprising a second input map with a time frame dimension and the range-velocity dimension for each angle channel of the second input data; and
third input data of the plurality of pieces of input data comprising a third input map with the time frame dimension and the angle dimension for each range-velocity channel of the third input data.
|