Human Motion Video & Ground Truth Rendering Framework (Sep. 2017 – Jul. 2018)

Imaging Media research Center, Korea Institute of Science and Technology (Seoul, South Korea)

Main Developer

C++ and Unreal Engine4

Human Motion Video & Ground Truth Rendering Framework (2017-Present)

Recently, machine learning techniques have been leveraged to train various robotics systems. One of the primary challenges with these techniques is the amount of data needed to adequately train the systems is prohibitively high. To tackle this problem, I am creating a rendering framework that composes a virtual world and synthesizes RGB video and ground truth sets with Unreal Engine 4.

Project Description

Configurable rendering framework to synthesize training dataset for training silver-care robot’s human motion recognition systems

Features

-Change camera viewpoint / light intensity

-Transition between day & night

-Show scene depth, joints position

-Output RGB & Ground Truth

-Dynamically loading FBX

-Change human appearance / motion

 

[ Demo Video ]

  • latest version ( with UI )
  • older version ( without UI )

One Comment

답글 남기기

아래 항목을 채우거나 오른쪽 아이콘 중 하나를 클릭하여 로그 인 하세요:

WordPress.com 로고

WordPress.com의 계정을 사용하여 댓글을 남깁니다. 로그아웃 /  변경 )

Google photo

Google의 계정을 사용하여 댓글을 남깁니다. 로그아웃 /  변경 )

Twitter 사진

Twitter의 계정을 사용하여 댓글을 남깁니다. 로그아웃 /  변경 )

Facebook 사진

Facebook의 계정을 사용하여 댓글을 남깁니다. 로그아웃 /  변경 )

%s에 연결하는 중