In Partial Fulfillment of the Requirements for the Degree of Master of Science
will defend his thesis
Towards A Change Detection In Laser Scanning Point Clouds
Obtaining unprecedented amount of topographic data is easier than ever. There has been very extensive research on analysis of satellite and aerial images, however automa tic change detection and geo-database updates remain a challenging task. The goal of this thesis is to develop algorithms for change detection and classification of large datasets in near real time. The specific objectives are to: (i) develop an algorithm for change detection, (ii) develop a an algorithm capable of classifying the change, (iii) evaluate the performance of these methods on representative datasets. We propose a method for near rea l time change detection on 3D point clouds. Our algorithm addresses the high dimensionality of the data issue by formulating the problem as an approximate nearest neighbour problem in a location frame. We have applied the algorithm to the 2002 and 2010 point cloud datasets of the Island of Galveston and have been able to detect and classify water, buildings, low, and high vegetation change. This analysis of LiDAR (Light Detection and Ranging) data is of huge significance as it provides an unique ability to measure high-resolution 3D change and can be used to provide accurate information to emergence response units in Natural Disasters such as Earthquakes, Hurricanes, and Tsunami.
Date: Friday, November 20, 2015
Time: 1:30 PM
Place: HBS 350
Advisor: Dr. Ioannis A. Kakadiaris
Faculty, students, and the general public are invited.