Abstract

Advancements permitting the rapid extraction of 3D point clouds from a variety of imaging modalities across the global landscape have provided a vast collection of high fidelity digital surface models. This has created a situation with unprecedented overabundance of 3D observations which greatly outstrips our current capacity to manage and infer actionable information. While years of research have removed some of the manual analysis burden for many tasks, human analysis is still a cornerstone of 3D scene exploitation. This is especially true for complex tasks which necessitate comprehension of scale, texture and contextual learning. In order to ameliorate the interpretation burden and enable scientific discovery from this volume of data, new processing paradigms are necessary to keep pace.

With this context, this dissertation advances fundamental and applied research in 3D point cloud data pre-processing and deep learning from a variety of platforms. We show that the representation of 3D point data is often not ideal and sacrifices fidelity, context or scalability. First ground scanning terrestrial LIght Detection And Ranging (LiDAR) models are shown to have an inherent statistical bias, and present a state of the art method for correcting this, while preserving data fidelity and maintaining semantic structure. This technique is assessed in the dense canopy of Micronesia, with our technique being the best at retaining high levels of detail under extreme down-sampling (< 1%). Airborne systems are then explored with a method which is presented to pre-process data to preserve a global contrast and semantic content in deep learners. This approach is validated with a building footprint detection task from airborne imagery captured in Eastern TN from the 3D Elevation Program (3DEP), our approach was found to achieve significant accuracy improvements over traditional techniques. Finally, topography data spanning the globe is used to assess past and previous global land cover change. Utilizing Shuttle Radar Topography Mission (SRTM) and Moderate Resolution Imaging Spectroradiometer (MODIS) data, paired with the airborne preprocessing technique described previously, a model for predicting land-cover change from topography observations is described.

The culmination of these efforts have the potential to enhance the capabilities of automated 3D geospatial processing, substantially lightening the burden of analysts, with implications improving our responses to global security, disaster response, climate change, structural design and extraplanetary exploration.

Library of Congress Subject Headings

Three-dimensional imaging--Data processing; Optical radar--Data processing; Aerial photogrammetry--Data processing; Spatial data infrastructures; Computer vision; Machine learning; Electronic noise

Publication Date

5-7-2020

Document Type

Dissertation

Student Type

Graduate

Degree Name

Imaging Science (Ph.D.)

Department, Program, or Center

Chester F. Carlson Center for Imaging Science (COS)

Advisor

Jan van Aardt

Advisor/Committee Member

David Ross

Advisor/Committee Member

Emmett Ientilucci

Campus

RIT – Main Campus

Plan Codes

IMGS-PHD

Download

Share

COinS