Description:

This project will develop a multi-human detection system using multiple depth cameras, such as RealSense/Kinect/Xtion, for indoor environment. We have a working system that detects where humans are, who they are as well as heights of them. This project will improve the current version, which is developed by part 4 students, and will be integrated to some of ongoing projects in the Robotics lab, such as Guide and logistics robot system. All necessary devices will be provided.

This project includes to:

• calibrate multi-cameras autonomously,
• do 3D reconstruction of the environment,
• find the positions and directions of humans more accurately,
• track the humans, and
• combine with other perception methods, such as face detection and recognition.

Project scope will be decided after the meeting with supervisors. You will bring to the role a passion for research and engineering, excellent computing skills (including a high level of programming ability), and a strong sense of responsibility. It will be better if you have an experience on vision processing and/or using 3D cameras.

Type:

Undergraduate

Outcome:

Prerequisites

None

Specialisations

• Computer Systems Engineering
• Software Engineering

Categories

• AI & Machine learning
• Human Computer Interactions
• Robotics

Supervisor

• Ho Seok Ahn

Co-supervisor

• JongYoon Lim

Team

• Parie Malhotra
• Grun Wua Wong

Lab

Lab allocations have not been finalised