Nicholas to Speak at FIT About His Dissertation Research
Greetings!
I come with excellent news today! This Friday, October 30, from noon to 1pm, I will be giving a talk at the Florida Institute of Technology (FIT) about my dissertation research, specifically my work with unsupervised building detection from Irregular LiDAR data. Dr. Georgios Anagnostopulos, one of the professors who served on my Dissertation Defense Committee, asked me to give a talk at FIT.
The talk will be in Room 118. FIT has a campus map hosted <here>.
The Abstract for the talk is as follows:
A novel paradigm is presented which employs homotopy trees, a branch of topography, for building detection in Light Detection and Ranging (LiDAR) data. The method is developed for irregularly spaced LiDAR data and therefore it can also be applied to rasterized/grid spaced data without any modifications. Using features extracted from either the first and/or last returns (if available) of the LiDAR pulses and the triangulation of the LiDAR data, the proposed method can discriminate ground from non-ground points and subsequently differentiate non-ground as building or non-building points. The method is unsupervised, no training phases are necessary. The only assumption the algorithm makes about the buildings is that they exist as structures which protrude from the ground with a minimal predefined area and height and have a roof. Results are provided for two different actual data sets without changing any of the algorithm’s parameters.
You can find a detailed description of this approach in my dissertation, in chapter 3.
You can find more information about this lecture <here on my research website>.
Tags: Building Detection, FIT, Florida Institute of Technology, LiDAR, N. Shorter, Nicholas, Nick, PHT, Pseudo Homotopy Trees, Shorter, TIN, Triangulated Irregular Network, Unsupervised Building Detection
October 27th, 2009 at 7:56 pm
i wish you luck on friday, god’s Speed.