US 11,790,541 B2
Method and apparatus with target object tracking
Jonghoon Yoon, Hwaseong-si (KR); Dongwook Lee, Suwon-si (KR); Changyong Son, Anyang-si (KR); Byung In Yoo, Seoul (KR); and Seohyung Lee, Seoul (KR)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed by SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed on Jul. 26, 2021, as Appl. No. 17/385,455.
Claims priority of application No. 10-2021-0034804 (KR), filed on Mar. 17, 2021.
Prior Publication US 2022/0301188 A1, Sep. 22, 2022
Int. Cl. G06T 7/246 (2017.01); G06V 10/75 (2022.01); G06F 18/22 (2023.01); H04N 23/63 (2023.01)
CPC G06T 7/248 (2017.01) [G06F 18/22 (2023.01); G06V 10/751 (2022.01); H04N 23/632 (2023.01); G06T 2200/24 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/20104 (2013.01); G06T 2207/20132 (2013.01); G06V 10/759 (2022.01)] 24 Claims
OG exemplary drawing
 
1. A processor-implemented method of tracking a target object, comprising:
extracting a feature from frames of an input image;
selecting a neural network model from among a plurality of neural network models provided in advance based on a feature value range, based on a feature value of a target object that is included in the feature of a previous frame among the frames; and
generating a bounding box of the target object included in a current frame among the frames, based on the selected neural network model.