US 12,243,240 B2
Apparatus and method with multi-image panoptic segmentation
Hui Zhang, Beijing (CN); Pingjun Li, Beijing (CN); Byung In Yoo, Seoul (KR); Hana Lee, Suwon-si (KR); and Yi Zhou, Beijing (CN)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed by Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed on Nov. 12, 2021, as Appl. No. 17/525,213.
Claims priority of application No. 202011272161.8 (CN), filed on Nov. 13, 2020; and application No. 10-2021-0130042 (KR), filed on Sep. 30, 2021.
Prior Publication US 2022/0156944 A1, May 19, 2022
Int. Cl. G06T 7/174 (2017.01); G06F 16/71 (2019.01); G06F 18/25 (2023.01); G06T 7/20 (2017.01); G06V 10/22 (2022.01); G06V 10/40 (2022.01)
CPC G06T 7/174 (2017.01) [G06F 16/71 (2019.01); G06F 18/253 (2023.01); G06T 7/20 (2013.01); G06V 10/22 (2022.01); G06V 10/40 (2022.01); G06T 2207/10016 (2013.01); G06T 2207/20081 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A processor-implemented method with video processing, the method comprising:
determining a first image feature of a first image of video data and a second image feature of a second image that is previous to the first image;
determining a time-domain information fusion processing result by performing time-domain information fusion processing on the first image feature and the second image feature; and
determining a panoptic segmentation result of the first image based on the time-domain information fusion processing result, wherein the time-domain information fusion processing result comprises a first time-domain integration feature of the first image feature and a second time-domain integration feature of the second image feature.