METHOD AND APPARATUS FOR POSE IDENTIFICATION

Organization Name

Samsung Electronics Co., Ltd.

Inventor(s)

Zhihua Liu of Beijing (CN)

Yamin Mao of Beijing (CN)

Hongseok Lee of Seoul (KR)

Paul Oh of Seongnam-si (KR)

Qiang Wang of Beijing (CN)

Yuntae Kim of Suwon-si (KR)

Weiheng Liu of Beijing (CN)

METHOD AND APPARATUS FOR POSE IDENTIFICATION - A simplified explanation of the abstract

This abstract first appeared for US patent application 18736088 titled 'METHOD AND APPARATUS FOR POSE IDENTIFICATION

The method described in the patent application involves identifying the pose of a target using a depth image, feature information, and position information.

Obtaining a depth image of the target.
Extracting feature information from the depth image.
Determining position information corresponding to the feature information.
Analyzing the feature information and position information to identify the pose of the target.

Potential Applications: This technology could be used in various fields such as robotics, computer vision, and augmented reality for accurate pose identification of objects or individuals.

Problems Solved: This technology addresses the challenge of accurately identifying the pose of a target using depth images and feature information.

Benefits: The method provides a more precise and reliable way to determine the pose of a target, which can be beneficial in applications requiring accurate spatial recognition.

Commercial Applications: This technology could be valuable in industries such as healthcare (for patient monitoring), gaming (for motion capture), and security (for surveillance systems).

Questions about Pose Identification: 1. How does this method improve upon existing pose identification techniques? 2. What are the potential limitations of using depth images for pose identification?

Original Abstract Submitted

Disclosed is a pose identification method including obtaining a depth image of a target, obtaining feature information of the depth image and position information corresponding to the feature information, and obtaining a pose identification result of the target based on the feature information and the position information.