公开(公告)号：US20230298357A1

公开(公告)日：2023-09-21

申请号：US17998179

申请日：2021-04-07

Applicant: SONY GROUP CORPORATION

Inventor： HSINGYING HO ,  CHRISTOPHER WRIGHT ,  NICHOLAS WALKER ,  BERNADETTE ELLIOT-BOWMAN

IPC: G06V20/58 ,  G06V10/82 ,  G06V10/764 ,  G06V20/17 ,  G06T7/70 ,  G06T11/00 ,  H04R1/08 ,  H04R3/00 ,  H04R23/00

CPC classification number: G06V20/58 ,  G06T7/70 ,  G06T11/00 ,  G06V10/764 ,  G06V10/82 ,  G06V20/17 ,  H04R1/08 ,  H04R3/00 ,  H04R23/008 ,  G06T2207/10032 ,  G06T2207/20084 ,  G06T2207/30252

Abstract: [Problem] The estimation accuracy of a class of an object is to be effectively improved. [Means of Solution] Provided is an information processing device including an estimation unit that estimates, based on an input image, a class of an object that is present in a real environment corresponding to an imaging range of the input image, wherein the object includes an acoustically useful object having an acoustic feature useful for class estimation, and the estimation unit estimates a class of the acoustically useful object based on acoustic data collected from around the acoustically useful object.

公开(公告)号：US20230215151A1

公开(公告)日：2023-07-06

申请号：US17998929

申请日：2021-05-14

Applicant: SONY GROUP CORPORATION

Inventor： YUKI YAMAMOTO ,  CHRISTOPHER WRIGHT ,  BERNADETTE ELLIOTT-BOWMAN ,  NICHOLAS WALKER

IPC: G06V10/776 ,  G06V10/778 ,  G06V10/98 ,  G06V10/24

CPC classification number: G06V10/776 ,  G06V10/778 ,  G06V10/993 ,  G06V10/24 ,  G06V20/58

Abstract: The present disclosure relates to an information processing apparatus, an information processing method, an information processing system, and a program capable of appropriately evaluating an object recognition filter by simpler processing. A generation unit that generates teacher data of a preprocessing filter provided in a preceding stage of the object recognition filter is generated by a cyclic generative adversarial network (Cyclic GAN) that is unsupervised learning. The teacher data generated by the generated generation unit is applied to the object recognition filter, an evaluation image is generated from a difference between object recognition result images, and an evaluation filter that generates an evaluation image from the evaluation image and the teacher data is generated. The evaluation filter is applied to an input image to generate an evaluation image, and the object recognition filter is evaluated by the generated evaluation image. The present disclosure can be applied to an object recognition device.

公开(公告)号：US20240414428A1

公开(公告)日：2024-12-12

申请号：US18700741

申请日：2022-10-14

Applicant: SONY GROUP CORPORATION

Inventor： SUSUMU TAKATSUKA ,  KENTA ENDO ,  CHRISTOPHER WRIGHT ,  BERNADETTE ELLIOTT-BOWMAN ,  NICHOLAS WALKER

IPC: H04N23/61 ,  G06N3/0464 ,  G06N3/067 ,  H04N23/11

Abstract: A neural network device includes a light receiving portion that receives light through an optical neural network, and a control unit that performs a predetermined control with detection of a predetermined target object based on a signal corresponding to light received by the light receiving portion as a trigger.