- Patent Title: Systems and methods for training pose estimators in computer vision
-
Application No.: US17393338Application Date: 2021-08-03
-
Publication No.: US12293535B2Publication Date: 2025-05-06
- Inventor: Agastya Kalra , Rishav Agarwal , Achuta Kadambi , Kartik Venkataraman , Anton Boykov
- Applicant: INTRINSIC INNOVATION LLC
- Applicant Address: US CA Mountain View
- Assignee: INTRINSIC INNOVATION LLC
- Current Assignee: INTRINSIC INNOVATION LLC
- Current Assignee Address: US CA Mountain View
- Agency: Fish & Richardson P.C.
- Main IPC: G06T7/70
- IPC: G06T7/70 ; H04N13/243 ; H04N23/56 ; H04N25/705

Abstract:
A data capture stage includes a frame at least partially surrounding a target object, a rotation device within the frame and configured to selectively rotate the target object, a plurality of cameras coupled to the frame and configured to capture images of the target object from different angles, a sensor coupled to the frame and configured to sense mapping data corresponding to the target object, and an augmentation data generator configured to control a rotation of the rotation device, to control operations of the plurality of cameras and the sensor, and to generate training data based on the images and the mapping data.
Public/Granted literature
- US20230041560A1 SYSTEMS AND METHODS FOR TRAINING POSE ESTIMATORS IN COMPUTER VISION Public/Granted day:2023-02-09
Information query