US 11,893,780 B2
Method and apparatus for image segmentation
Jianlong Yuan, Beijing (CN); Hanchao Jia, Beijing (CN); Shu Wang, Beijing (CN); and Zhenbo Luo, Beijing (CN)
Assigned to Samsung Electronics Co., Ltd
Appl. No. 17/294,020
Filed by Samsung Electronics Co., Ltd., Gyeonggi-do (KR)
PCT Filed Nov. 15, 2019, PCT No. PCT/KR2019/015702
§ 371(c)(1), (2) Date May 14, 2021,
PCT Pub. No. WO2020/101448, PCT Pub. Date May 22, 2020.
Claims priority of application No. 201811361168.X (CN), filed on Nov. 15, 2018.
Prior Publication US 2022/0004808 A1, Jan. 6, 2022
Int. Cl. G06V 10/82 (2022.01); G06T 7/136 (2017.01); G06T 7/11 (2017.01); G06F 18/213 (2023.01); G06F 18/24 (2023.01); G06F 18/25 (2023.01); G06V 10/26 (2022.01)
CPC G06V 10/82 (2022.01) [G06F 18/213 (2023.01); G06F 18/24 (2023.01); G06F 18/253 (2023.01); G06T 7/11 (2017.01); G06T 7/136 (2017.01); G06V 10/26 (2022.01)] 19 Claims
OG exemplary drawing
 
14. An apparatus of an electronic device, comprising:
a feature extraction module; and
a feature map processing module,
the feature extraction module being configured to:
perform feature extraction on an image through a feature extraction network to obtain a feature map as a three-dimensional matrix, wherein directions of the feature map include a first direction, a second direction, and a third direction, and
the feature map processing module being configured to:
perform feature map processing on the feature map using a convolution operation or a pooling operation for at least two of the directions of the feature map to complete semantic segmentation of the image,
wherein the first direction, the second direction, and the third direction are orthogonal to each other.