3D point cloud analysis

• Main Author: Chiong, Mervyn Jia Rong
• Other Authors: Lu Shijian
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2022
• Subjects: Engineering::Computer science and engineering
• Online Access: https://hdl.handle.net/10356/163348
• Institution: Nanyang Technological University

In this paper, I propose a novel idea to tackle the 3D Point Cloud Object Detection and Segmentation research topic called Transfer Fusion. It will be used in tandem with M2Track and I will also be exploring the differences between M2Track as a standalone versus with TF. M2Tracks uses a motion-centric paradigm as the main focus to get the results. Whereas Transfer Fusion, relies on overlapping data from 2 different sources to obtain depth perception and additional information that may assist in the boosting of the accuracy and precision rates. Additionally, I will highlight the differences, create hypothesis from the results and also provide the grounds for further research to be done in this field.