Edge-Preserving Optimisation and Meshing of Indoor Environment Point Cloud

  • 皮 安卓

Student thesis: Master's Thesis

Abstract

This Master’s Thesis focus on the processing of indoor point clouds from their registration using a RGB-D camera to the color meshing of their optimised version On the images coming from the camera keypoints are robustly localised using scale-invariant feature transform algorithm and computed through the bag of words model These features are then compared in order to merge the successive images and the corresponding point clouds as well as executing loop closure The obtained point cloud is separated in two categories The edges are cleaned and reinforced in order to preserve them all along the project The remaining surface points are reduced in number while focusing again of the edge preservation The optimised point cloud is meshed using ball pivoting algorithm with two different ball radius for different edge and surface point densities The output of this project is the optimised color mesh of a previously registered point cloud
Date of Award2019
Original languageEnglish
SupervisorJiun-Haur Tarn (Supervisor)

Cite this

Edge-Preserving Optimisation and Meshing of Indoor Environment Point Cloud
安卓, 皮. (Author). 2019

Student thesis: Master's Thesis