Using Object-Based Classification of Aerial Photography to Measure Change in Crop Field Size Between 1938 and Present in Michigan, USA

Authors: Rhett Mohler*, Saginaw Valley State University
Topics: Remote Sensing, Land Use and Land Cover Change
Keywords: aerial photography, object-based classification, land cover change
Session Type: Poster
Day: 4/13/2018
Start / End Time: 5:20 PM / 7:00 PM
Room: Napoleon Foyer/Common St. Corridor, Sheraton, 3rd Floor
Presentation File: No File Uploaded

Historical aerial photos contain large amounts of information that is invaluable to long-term studies of land cover change. This is particularly true since these images were collected systematically as early as the 1930s. The purpose of this study was to determine the change in agricultural field size between the 1930s and present using object-based classification. This information is useful to historians, land managers, environmental modelers, and any other entity interested in land cover change over time. Object-based classification promises to be extremely useful to this and similar endeavors because it can systematically overcome the effects of vignetting in early aerial photos, and because it can use the geometric information in these photos. Results showed that object-based classification did in fact help to accurately characterize land cover in older images with vignetting problems and provide good estimates of agricultural field size change.

Abstract Information

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

To access contact information login