公开(公告)号：US11380114B2

公开(公告)日：2022-07-05

申请号：US16849015

申请日：2020-04-15

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Biao Wang ,  Chao Zhang ,  Changkyu Choi ,  Deheng Qian ,  Jae-Joon Han ,  Jingtao Xu ,  Hao Feng

IPC: G06V30/194 ,  G06N3/04 ,  G06N3/08 ,  G06K9/62 ,  G06V10/32

Abstract: A method of detecting a target includes generating an image pyramid based on an image on which a detection is to be performed; classifying candidate areas in the image pyramid using a cascade neural network; and determining a target area corresponding to a target included in the image based on the plurality of candidate areas, wherein the cascade neural network includes a plurality of neural networks, and at least one neural network among the neural networks includes parallel sub-neural networks.

公开(公告)号：US10657424B2

公开(公告)日：2020-05-19

申请号：US15825951

申请日：2017-11-29

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Biao Wang ,  Chao Zhang ,  Changkyu Choi ,  Deheng Qian ,  Jae-Joon Han ,  Jingtao Xu ,  Hao Feng

IPC: G06K9/66 ,  G06N3/04 ,  G06K9/42 ,  G06N3/08 ,  G06K9/62

Abstract: A method of detecting a target includes generating an image pyramid based on an image on which a detection is to be performed; classifying candidate areas in the image pyramid using a cascade neural network; and determining a target area corresponding to a target included in the image based on the plurality of candidate areas, wherein the cascade neural network includes a plurality of neural networks, and at least one neural network among the neural networks includes parallel sub-neural networks.