- Patent Title: Generation method for training dataset, model generation method, training data generation apparatus, inference apparatus, robotic controller, model training method and robot
-
Application No.: US16895233Application Date: 2020-06-08
-
Publication No.: US11590650B2Publication Date: 2023-02-28
- Inventor: Kenta Yonekura , Kuniyuki Takahashi
- Applicant: Preferred Networks, Inc.
- Applicant Address: JP Tokyo
- Assignee: Preferred Networks, Inc.
- Current Assignee: Preferred Networks, Inc.
- Current Assignee Address: JP Tokyo
- Agency: IPUSA, PLLC
- Priority: JPJP2019-108219 20190610,JPJP2019-164343 20190910,JPJP2020-039132 20200306
- Main IPC: G06T7/73
- IPC: G06T7/73 ; B25J9/16 ; B25J19/02
Abstract:
One aspect of the present disclosure relates to a generation method for a training dataset, comprising: capturing, by one or more processors, a target object to which a marker unit recognizable under a first illumination condition is provided; and acquiring, by the one or more processors, a first image where the marker unit is recognizable and a second image obtained by capturing the target object under a second illumination condition.
Information query
