US 12,148,211 B2
Image processing apparatus and 3D model generation method
Hiroaki Takahashi, Tokyo (JP); and Tetsuya Fukuyasu, Tokyo (JP)
Assigned to SONY GROUP CORPORATION, Tokyo (JP)
Appl. No. 17/594,052
Filed by SONY GROUP CORPORATION, Tokyo (JP)
PCT Filed Mar. 27, 2020, PCT No. PCT/JP2020/014171
§ 371(c)(1), (2) Date Sep. 30, 2021,
PCT Pub. No. WO2020/209108, PCT Pub. Date Oct. 15, 2020.
Claims priority of application No. 2019-076107 (JP), filed on Apr. 12, 2019.
Prior Publication US 2022/0172474 A1, Jun. 2, 2022
Int. Cl. G06V 20/40 (2022.01); G06T 17/00 (2006.01); G06V 10/25 (2022.01); H04N 13/189 (2018.01); H04N 13/243 (2018.01)
CPC G06V 20/41 (2022.01) [G06T 17/00 (2013.01); G06V 10/25 (2022.01); H04N 13/189 (2018.05); H04N 13/243 (2018.05)] 17 Claims
OG exemplary drawing
 
1. An image processing apparatus, comprising:
an image input unit configured to acquire a plurality of multi-view images of a subject from a plurality of image capturing devices, wherein
the plurality of image capturing devices captures the plurality of multi-view images from a plurality of viewpoints,
the plurality of multi-view images includes a subject image, and
the subject image is captured by a first image capturing device, of the plurality of image capturing devices, from a specific viewpoint of the plurality of viewpoints;
a generation unit configured to:
generate a plurality of image capturing ranges of the plurality of image capturing devices based on the plurality of multi-view images; and
generate a first 3D region of the plurality of image capturing ranges based on the plurality of multi-view images;
a projection unit configured to:
project the first 3D region onto the specific viewpoint; and
generate a first region image based on the projected first 3D region; and
a determination unit configured to determine that the subject is out of the plurality of image capturing ranges based on each of:
the generated first region image, and
the subject image.