6533b851fe1ef96bd12a987b

RESEARCH PRODUCT

Shoreline Extraction and Change Detection using 1:5000 Scale Orthophoto Maps: A Case Study of Latvia-Riga

subject

description

Coastal management requires rapid, up-to-date, and
 correct information. Thus, the determination of coastal movements and its
 directions has primary importance for coastal managers. For monitoring the
 change of shorelines, remote sensing data, very high resolution aerial images
 and orthophoto maps are utilized for detections of change on shorelines. It is
 possible to monitor coastal changes by extracting the coastline from orthophoto
 maps. Along the Baltic Sea and Riga Gulf, Latvian coastline length is 496 km.
 It is rich of coastal resources and natural biodiversity.  Around 120 km of coastline are affected by
 significant coastal changes caused by climate change, storms, erosion, human
 activities and other reasons and they must be monitored. In this study, an
 object-oriented approach has been proposed to detect shoreline and detect the
 changes by using 1:5000 scaled orthophoto maps of Riga-Latvia (3bands, R, G,
 and NIR) in the years of 2007 and 2013. As many of the authors have mentioned,
 object-oriented classification method can be more successful than the
 pixel-based methods especially for high resolution images to avoid
 mix-classification. In the presented study the eCognition object-oriented fuzzy
 image processing software has been used. The results were compared to the
 results derived from manual digitizing. Extracted and manually digitized
 shorelines have been divided in 5 m segments in x axis. The y coordinates of
 the new nodes were taken from the original “.dxf” file or computed by
 interpolation. Thus, the RMS errors of selected points were calculated