TIME-SERIES OF SHORELINE CHANGE FROM PUBLICLY AVAILABLE SATELLITE IMAGERY

摘要

Although observations of shoreline variability are essential to regulate coastal development and design coastal protection, long-term uninterrupted time series of shoreline variability and changes remain very rare along much of the world’s coastlines. Satellite remote sensing can provide low-cost long-term shoreline data capable of resolving the temporal scales of interest to coastal scientists and engineers at sites where no in-situ field measurements are available. The shoreline detection algorithm presented here is optimized for sandy beach coastlines and combines a sub-pixel border segmentation and an image classification component, which refines the segmentation into four distinct categories such that the shoreline detection is specific to the sand/water interface.