Estimator training method and pose estimating method using depth image
AssigneesSamsung Electronics Co., Ltd., Imperial Innovations Limited
InventorsJae Joon Han, Danhang Tang, Tae Kyun Kim, Seung Ju Han, Byung In Yoo, Chang Kyu Choi, Alykhan Tejani, Hyung Jin Chang
Life of this patent
Estimating the term…
Abstract
An estimator training method and a pose estimating method using a depth image are disclosed, in which the estimator training method may train an estimator configured to estimate a pose of an object, based on an association between synthetic data and real data, and the pose estimating method may estimate the pose of the object using the trained estimator.
Claims16
A method of training an estimator to estimate a pose of an object, the method comprising:
- obtaining a latent tree model of the object;
- and
- generating, by way of a processor, a vector pair configured to partition input data received at a latent node into two parts, with respect to a plurality of latent nodes positioned along paths from a root node to a plurality of leaf nodes of the latent tree model, wherein two vectors included in the vector pair are configured to have directions from a center of the input data toward centers of the partitioned two parts.
A method of estimating a pose, the method comprising:
- detecting a plurality of parts of an object included in an input image using an estimator trained based on a latent tree model of the object;
- and
- estimating, by way of a processor, a pose of the object based on the detected plurality of parts, wherein the estimator is trained by generating a vector pair configured to partition input data received at a latent node into two parts, with respect to a plurality of latent nodes positioned along paths from a root node to a plurality of leaf nodes of the latent tree model, wherein two vectors included in the vector pair are configured to have directions from a center of the input data toward centers of the partitioned two parts.
Dependencies are inferred from the claim text.