US 12,125,284 B2
Object search device and object search method
Masato Tamura, Tokyo (JP); Tomoaki Yoshinaga, Tokyo (JP); Atsushi Hiroike, Tokyo (JP); Hiromu Nakamae, Tokyo (JP); and Yuta Yanashima, Tokyo (JP)
Assigned to Hitachi, Ltd., Tokyo (JP)
Appl. No. 17/784,472
Filed by Hitachi, Ltd., Tokyo (JP)
PCT Filed Oct. 13, 2020, PCT No. PCT/JP2020/038659
§ 371(c)(1), (2) Date Jun. 10, 2022,
PCT Pub. No. WO2021/131248, PCT Pub. Date Jul. 1, 2021.
Claims priority of application No. 2019-232512 (JP), filed on Dec. 24, 2019.
Prior Publication US 2023/0005268 A1, Jan. 5, 2023
Int. Cl. G06V 20/52 (2022.01); G06V 10/82 (2022.01); G06V 20/64 (2022.01)
CPC G06V 20/52 (2022.01) [G06V 10/82 (2022.01); G06V 20/647 (2022.01); G06V 2201/07 (2022.01)] 11 Claims
OG exemplary drawing
 
1. An object search device, comprising:
an image feature extraction unit that is configured with a first neural network, and is configured to input an image to extract an image feature;
a three-dimensional data feature extraction unit that is configured with a second neural network, and is configured to input three-dimensional data to extract a three-dimensional data feature;
a learning unit that is configured to extract an image feature and a three-dimensional data feature from an image and three-dimensional data of an object that are obtained from a same individual, respectively, and update an image feature extraction parameter so as to reduce a difference between the image feature and the three-dimensional data feature; and
a search unit that is configured to extract image features of a query image and a gallery image of the object by the image feature extraction unit using the updated image feature extraction parameter, and calculate a similarity between the image features of both images to search for the object.