An object-based classification of urban land use and wetland vegetation cover from hyperspatial, multispectral UAS imagery

Authors: Whitney Broussard*, JESCO Environmental and Geotechnical Services, Inc., Jenneke M. Visser, University of Louisiana at Lafayette, Robert P. Brooks, The Pennsylvania State University, Tom Cousté, JESCO Environmental and Geotechnical Services, Inc.
Topics: Remote Sensing, Land Use and Land Cover Change, Marine and Coastal Resources
Keywords: Unmanned Aircraft Systems, Object-Based Image Analysis
Session Type: Paper
Day: 4/13/2018
Start / End Time: 5:20 PM / 7:00 PM
Room: Balcony M, Marriott, River Tower Elevators, 4th Floor
Presentation File: No File Uploaded


Recent developments in Unmanned Aircraft Systems (UAS) have sparked interest in the ability of these systems to capture remotely sensed data to monitor changing land cover in both urban and natural landscapes. Here, we demonstrate the ability of UAS technology to collect hyperspatial, multispectral aerial images and produce 2-dimensional orthomosaics and 2.5-dimensional digital surface models in an intermediate coastal marsh and a rural community in southern Louisiana. We then use Object-Based Image Analysis (OBIA) techniques to classify the UAS-derived data stacks. In the urban community, we classified building footprints, tree and forest canopy, impervious cover, and open water. In the intermediate marsh, we classified species composition and quantified average plant height, land-water interface, and Normalized Difference Vegetation Index (NDVI). Model results were validated with on-the-ground surveys. We suggest that these OBIA methods could be readily applied in multiple urban and coastal settings and could support other project operations and monitoring needs, such as flood mapping and disaster response. Such a method would be an important step towards comprehensive assessment and monitoring programs.

Abstract Information

This abstract is already part of a session. View the session here.

To access contact information login