Land Cover Classification Comparison between Object Based Image Analysis (OBIA) and Manual Interpretation of Aerial Photography

Authors: Sofia Simela Kozidis*, University of Wisconsin - La Crosse
Topics: Land Use and Land Cover Change, Remote Sensing, Spatial Analysis & Modeling
Keywords: OBIA, Upper Mississippi River, Aerial Photography
Session Type: Poster
Day: 4/13/2018
Start / End Time: 1:20 PM / 3:00 PM
Room: Napoleon Foyer/Common St. Corridor, Sheraton, 3rd Floor
Presentation File: No File Uploaded

This research is to analyze a subsection of mosaiced, orthorectified, color-infrared aerial photography captured in 2010/2011 from Pool 5 of the Upper Mississippi River. The photography is examined and processed using two different Geographic Information Systems (GIS) software, Overwatch Textron Systems' Feature Analyst on ArcGIS platform and Trimble's eCognition Developer, to conduct geospatial object-based image analysis (OBIA). These are used to classify the image into different land cover/use categories based on General Wetland Vegetation Classification System Levels I, II, and III used by the United States Geological Survey's Land Cover Institute. The results from each OBIA program are then compared to one another for accuracy and efficiency and ultimately compared to the manually classified results completed by the U.S. Army Corps of Engineers' Upper Mississippi River Restoration Program (UMRR), Long Term Resource Monitoring (LTRM), and U.S. Geological Survey's Upper Midwest Environmental Sciences Center (UMESC) in early 2016. The goal is to determine whether OBIA can help professionals maintain or surpass their accuracy of manual interpretation to produce results in a fraction of the time needed for traditional methods. This study may provide insight on a near future where accurate land cover classification results can be produced promptly when responding to changes on the earth's surface.

Abstract Information

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

To access contact information login