US 12,462,390 B2
Hierarchical occlusion module and unseen object amodal instance segmentation system and method using the same
Seunghyeok Back, Gwangju (KR); Kyoobin Lee, Gwangju (KR); Joosoon Lee, Gwangju (KR); Taewon Kim, Gwangju (KR); Raeyoung Kang, Gwangju (KR); Sangjun Noh, Gwangju (KR); and Seongho Bak, Gwangju (KR)
Assigned to GWANGJU INSTITUTE OF SCIENCE AND TECHNOLOGY, Gwangju (KR)
Filed by GWANGJU INSTITUTE OF SCIENCE AND TECHNOLOGY, Gwangju (KR)
Filed on Sep. 23, 2022, as Appl. No. 17/951,282.
Claims priority of application No. 10-2022-0029692 (KR), filed on Mar. 8, 2022.
Prior Publication US 2023/0289971 A1, Sep. 14, 2023
Int. Cl. G06T 7/11 (2017.01); G06T 7/50 (2017.01); G06V 10/25 (2022.01); G06V 10/44 (2022.01); G06V 10/56 (2022.01); G06V 10/764 (2022.01); G06V 10/80 (2022.01); G06V 10/82 (2022.01)
CPC G06T 7/11 (2017.01) [G06T 7/50 (2017.01); G06V 10/25 (2022.01); G06V 10/44 (2022.01); G06V 10/56 (2022.01); G06V 10/764 (2022.01); G06V 10/806 (2022.01); G06V 10/82 (2022.01); G06T 2207/10024 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A hierarchical occlusion inference method performed by at least one processor of a computer system, comprising:
acquiring an image feature and an object region of interest feature derived from a cluttered scene image including at least one object instance, by the computer system;
deriving a bounding box feature of the object instance from the image feature and the object region of interest feature, by the computer system;
deriving a visible feature of the object instance by fusing the object region of interest feature and the bounding box feature, by the computer system;
deriving an occlusion including region feature of the object instance by fusing the object region of interest feature and the visible feature, by the computer system; and
deriving an occlusion including region mask of the object instance from the occlusion including region feature, by the computer system,
wherein the deriving of a bounding box feature of the object instance from the image feature and the object region of interest feature, by the computer system, includes:
deriving the bounding box feature of the object instance based on a region of interest color-depth feature pyramid network (FPN) feature and the object region of interest feature derived from the cluttered scene image including at least one object instance, by the computer system.