US 12,169,250 B2
Method and apparatus with radar data recognition
Insoo Kim, Seongnam-si (KR); Seungju Han, Seoul (KR); and Jaejoon Han, Seoul (KR)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed by Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed on Jul. 18, 2023, as Appl. No. 18/354,179.
Application 18/354,179 is a continuation of application No. 17/019,672, filed on Sep. 14, 2020, granted, now 11,747,442.
Claims priority of application No. 10-2019-0164500 (KR), filed on Dec. 11, 2019; and application No. 10-2020-0041721 (KR), filed on Apr. 6, 2020.
Prior Publication US 2023/0366982 A1, Nov. 16, 2023
Int. Cl. G01S 7/41 (2006.01); G06F 21/44 (2013.01)
CPC G01S 7/412 (2013.01) [G06F 21/44 (2013.01)] 23 Claims
OG exemplary drawing
 
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 to confirm an identity 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 performing a recognition operation of the object comprises:
extracting a first extracted feature data from a first input data with a first dimension configuration, using a first feature extraction model corresponding to the first dimension configuration among the plurality of feature extraction models,
extracting a second extracted feature data from a second input data with a second dimension configuration, using a second feature extraction model corresponding to the second dimension configuration among the plurality of feature extraction models; and
identifying the identity of the object based on the first extracted feature data and the second extracted feature data to confirm the identity of the object.