Dynamic object tracking with 3D depth data

• Main Author: Ng, Xuan Yi
• Other Authors: Cuong Dang
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2022
• Subjects: Engineering::Electrical and electronic engineering
• Online Access: https://hdl.handle.net/10356/157553
• Institution: Nanyang Technological University

I am joining the Robotics & Autonomous Systems department (RAS) in I2R research institute at A*STAR, which comprises three units: mobility, perception, and manipulation. The team I am working with focuses on research on mapping and localisation, which is categorized under mobility unit. This document is the final report for the final year project titled ‘Dynamic Object Tracking with 3D Depth Data’. The aim of this final report is to note down the progress throughout the Final Year Project and achievements of the project, as well as issues faced. The main objective of this project is to benchmark state of the art algorithms which perform semantic segmentation on 3D data, to tailor it for our specific use-case, and integrate it to a mapping and localisation pipeline for mobile robots. Eventually, it will be tested to evaluate if it can improve performances.