公开(公告)号：US20230154016A1

公开(公告)日：2023-05-18

申请号：US18155349

申请日：2023-01-17

Applicant: CANON KABUSHIKI KAISHA

Inventor： SHUHEI OGAWA

IPC: G06T7/246 ,  G06V10/74 ,  G06V10/82

CPC classification number: G06T7/248 ,  G06V10/82 ,  G06V10/761 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30196

Abstract: An information processing apparatus configured to track a specific object in images captured at a plurality of times includes a retaining unit configured to retain a feature quantity of a tracking target based on a learned model configured to detect a position of a predetermined object in an input image, an acquisition unit configured to acquire feature quantities of objects in a plurality of images based on the learned model, a detection unit configured to detect a candidate object similar to the tracking target based on the feature quantity of the tracking target and the feature quantities of the objects acquired from the plurality of images, and an identification unit configured to identify a correlation between the candidate object detected in a first image and the candidate object in a second image captured at a different time from the first image among the plurality of images.

公开(公告)号：US20230325671A1

公开(公告)日：2023-10-12

申请号：US18187577

申请日：2023-03-21

Applicant: CANON KABUSHIKI KAISHA

Inventor： SHUHEI OGAWA ,  SHUNTA TATE

IPC: G06N3/082

CPC classification number: G06N3/082

Abstract: The present disclosure makes it possible to learn a neural network architecture for achieving a sufficient inference accuracy while preventing an increase in the amount of processing. An information processing apparatus configured to learn an architecture for optimizing a structure of a neural network generates a plurality of candidates for an edge of the neural network, inputs learning data to the neural network with weight coefficients set to these candidates for the edge, and obtains an inference result. The information processing apparatus calculates a loss of the neural network based on a specified candidate number which is the number of candidates to be selected from the plurality of candidates and on the inference result, and then updates the weight coefficients for the plurality of candidates based on the loss. The information processing apparatus then selects candidates from the plurality of candidates based on the updated weight coefficients.

公开(公告)号：US20230316540A1

公开(公告)日：2023-10-05

申请号：US18189930

申请日：2023-03-24

Applicant: CANON KABUSHIKI KAISHA

Inventor： SHUHEI OGAWA

IPC: G06T7/20 ,  G06T7/70 ,  G06V10/44 ,  G06V10/74

CPC classification number: G06T7/20 ,  G06T7/70 ,  G06V10/44 ,  G06V10/761 ,  G06V2201/07

Abstract: An information processing apparatus detects a collation target from an image and obtains a predetermined evaluation value between the collation target previously detected and the collation target detected from the image. The information processing apparatus performs collation processing on the collation target detected from the image and the collation target previously detected based on the evaluation value obtained for the collation target detected from the image and a distribution of evaluation values previously obtained.