US 12,136,256 B2
Learning apparatus, learning method, and non-transitory computer-readable medium in which learning program has been stored
Takashi Shibata, Tokyo (JP); Hiroyoshi Miyano, Tokyo (JP); Eiji Kaneko, Tokyo (JP); Masato Toda, Tokyo (JP); Tsubasa Minematsu, Fukuoka (JP); Atsushi Shimada, Fukuoka (JP); and Rin-Ichiro Taniguchi, Fukuoka (JP)
Assigned to NEC CORPORATION, Tokyo (JP); and Kyushu University, National University Corporation, Fukuoka (JP)
Appl. No. 17/641,913
Filed by NEC Corporation, Tokyo (JP); and KYUSHU UNIVERSITY, NATIONAL UNIVERSITY CORPORATION, Fukuoka (JP)
PCT Filed Jun. 17, 2020, PCT No. PCT/JP2020/023844
§ 371(c)(1), (2) Date Mar. 10, 2022,
PCT Pub. No. WO2021/049119, PCT Pub. Date Mar. 18, 2021.
Claims priority of application No. 2019-167778 (JP), filed on Sep. 13, 2019.
Prior Publication US 2022/0327813 A1, Oct. 13, 2022
Int. Cl. G06V 10/774 (2022.01); G06V 10/22 (2022.01); G06V 10/762 (2022.01); G06V 10/764 (2022.01); G06V 20/70 (2022.01)
CPC G06V 10/7753 (2022.01) [G06V 10/22 (2022.01); G06V 10/762 (2022.01); G06V 10/764 (2022.01); G06V 20/70 (2022.01); G06V 2201/07 (2022.01)] 18 Claims
OG exemplary drawing
 
1. A learning apparatus comprising:
at least one memory configured to store instructions; and
at least one processor configured to execute the instructions to:
detect, as a candidate region of a learning target, a region detected by one of first detection processing of detecting an object region from a predetermined image and second detection processing of detecting a change region from background image information and the image, and not detected by the other;
output at least a part of the candidate region as a labeling target; and
learn a model for performing the first detection processing or a model for performing the second detection processing by using the labeling target being labeled as learning data.