US 11,695,928 B2
Dividing pattern determination device capable of reducing amount of computation, dividing pattern determination method, learning device, learning method, and storage medium
Dai Miyauchi, Chiba (JP)
Assigned to Canon Kabushiki Kaisha, Tokyo (JP)
Filed by CANON KABUSHIKI KAISHA, Tokyo (JP)
Filed on Apr. 19, 2021, as Appl. No. 17/234,609.
Claims priority of application No. 2020-079325 (JP), filed on Apr. 28, 2020.
Prior Publication US 2021/0334603 A1, Oct. 28, 2021
Int. Cl. G06K 9/62 (2022.01); G06K 9/20 (2006.01); G06K 9/46 (2006.01); G06N 3/08 (2023.01); H04N 19/96 (2014.01); H04N 19/30 (2014.01); H04N 19/119 (2014.01); G06N 3/084 (2023.01); G06V 10/22 (2022.01); G06V 10/40 (2022.01); G06F 18/21 (2023.01); G06F 18/213 (2023.01); G06V 10/77 (2022.01); G06V 10/778 (2022.01)
CPC H04N 19/119 (2014.11) [G06F 18/213 (2023.01); G06F 18/2193 (2023.01); G06N 3/084 (2013.01); G06V 10/22 (2022.01); G06V 10/40 (2022.01); G06V 10/7715 (2022.01); G06V 10/7796 (2022.01); H04N 19/30 (2014.11); H04N 19/96 (2014.11)] 15 Claims
OG exemplary drawing
 
1. A device comprising:
at least one processor; and
a memory coupled to the at least one processor, the memory having instructions that, when executed by the processor, perform the operations comprising:
inputting a first image of 64×64 pixels to a learning model and causing the learning model to generate a dividing pattern map for the first image of 64×64 pixels, the learning model having been subjected to machine learning, using images as input data and dividing pattern maps as teacher data; and
using the dividing pattern map generated for the first image to determine one or more sizes of sub-blocks to be used for dividing the first image,
wherein the dividing pattern map includes pieces of data corresponding to 16 prediction areas given by dividing the first image of 64×64 pixels into 4×4 blocks, respectively, and each of the pieces of data includes information indicative of which of a sub-block of 64×64 pixels, 4-division sub-blocks of 32×32 pixels, 16-division sub-blocks of 16×16 pixels, or 32-division sub-blocks of 8×8 pixels are to be used in corresponding one of the 4×4 blocks, as the sub-blocks to be used for dividing the first image.