Abstract
Historically, information was derived from images through manual interpretation and analysis. This process, while slow, proved to be highly accurate and reliable. In the 1970s, the advent of digital remote sensing technologies coupled with advances in computer processing led to the development of automated feature extraction techniques. Despite substantial investments in the technology, most automated approaches to remote sensing feature extraction fail to approach the accuracy of good old fashioned manual interpretation. Things, however, are starting to change. Object-based techniques, which have the ability to mimic human cognition, are proving to be highly successful in automating feature extraction, particularly from disparate data sets. This presentation will introduce object-based image analysis concepts and workflows drawing from recent coastal and terrestrial remote sensing projects.
Presenter Bio
Jarlath O’Neil-Dunne is the Director of the University of Vermont’s (UVM) Spatial Analysis Laboratory (SAL). He is a faculty member in the Rubenstein School of the Environment and Natural Resources and a faculty associate in UVM’s Transportation Research Center (TRC). Over the years his research has focused on the application of geospatial technology to a broad set of natural resource, urban planning, transportation, and national security issues. He has expertise in the application of object-based image analysis techniques, unmanned aerial systems, and spatial modeling. In addition to his duties at UVM Jarlath serves on the Board of Directors for AmericaView and the Vermont Center for Geographic Information Systems. He earned a B.S.F in Forest Science from the University of New Hampshire, an M.S. in Water Resources from the University of Vermont, and certificates in hyperspectral image exploitation and joint GIS operations from the National Geospatial Intelligence College. He also holds a certificate in Leadership and Management from the University of Vermont. Jarlath is a former officer in the United States Marine Corps where he served in East Africa, the Middle East, and East Asia. During the early stages of Operation Iraqi Freedom he co-directed the Marine Corps’ imagery intelligence assets.
Publication Date
11-21-2014
Document Type
Presentation
Recommended Citation
O'Neil-Dunne, Jarlath, "Object-Based Approaches to Remote Sensing Data Analysis" (2014). Seminars. 160.
https://scholars.unh.edu/ccom_seminars/160