US 12,085,394 B2
Electronic apparatus for object recognition and control method thereof
Eunseo Kim, Suwon-si (KR); Yehoon Kim, Suwon-si (KR); Chanwon Seo, Suwon-si (KR); Inhak Na, Suwon-si (KR); and Myungjin Eom, Suwon-si (KR)
Assigned to SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed by SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed on Jul. 28, 2023, as Appl. No. 18/227,345.
Application 18/227,345 is a continuation of application No. 17/493,930, filed on Oct. 5, 2021, granted, now 11,719,544, issued on Aug. 8, 2023.
Application 17/493,930 is a continuation of application No. 16/890,337, filed on Jun. 2, 2020, granted, now 11,151,357, issued on Oct. 19, 2021.
Claims priority of application No. 10-2019-0065519 (KR), filed on Jun. 3, 2019; application No. 10-2019-0099904 (KR), filed on Aug. 14, 2019; and application No. 10-2019-0122580 (KR), filed on Oct. 2, 2019.
Prior Publication US 2023/0366682 A1, Nov. 16, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G01C 21/20 (2006.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/10 (2022.01); G06V 20/64 (2022.01)
CPC G01C 21/206 (2013.01) [G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/10 (2022.01); G06V 20/64 (2022.01)] 20 Claims
OG exemplary drawing
 
1. An electronic apparatus, comprising:
a camera;
a storage for storing information on a map, a first layer, and a plurality of second layers which respectively corresponds to a plurality of areas in the map; and
at least one processor configured to:
identify a second layer corresponding to an area in which the electronic apparatus is located from among a plurality of areas in the map, from among the plurality of second layer based on information on an area in which the electronic apparatus is located from among a plurality of areas in the map,
identify an artificial intelligence model corresponding to the area from among a plurality of artificial intelligence model, based on the first layer and the identified second layer, and
input an image obtained through the camera to the identified artificial intelligence model to identify an object,
wherein the plurality of artificial intelligence model are trained to identify at least one object respectively located in a plurality of areas in the map.