Segmentation of planar surfaces from range data

• Main Author: Son, Ik Soo.
• Other Authors: Sung, Eric
• Format: Theses and Dissertations
• Language: English
• Published: 2009
• Subjects: DRNTU::Engineering::Electrical and electronic engineering
• Online Access: http://hdl.handle.net/10356/19684
• Institution: Nanyang Technological University

This project is the first part of a long term project that aims to develop a complete three-dimensional object recognition system from range data for industrial applications. The objective of this project is to develop a robust algorithm to extract all the planar surfaces from range data using region growing technique controlled by least-square criterion to accomplish the task of segmentation. This project will therefore form the foundation for further improvement for extracting of higher order surfaces, three-dimensional feature representation and ultimately object recognition. The planar surface segmentation algorithm is then to be tested by using both synthetic data and experimental data for evaluation.