Quantitative Assessment for Detection and Monitoring of Coastline Dynamics with Temporal RADARSAT Images

摘要: This study aims to detect coastline changes using temporal synthetic aperture radar (SAR) images for the state of Kelantan, Malaysia. Two active images, namely, RADARSAT-1 captured in 2003 and RADARSAT-2 2014, were used monitor such changes. We applied noise removal edge detection filtering on RADARSAT preprocessing remove salt pepper distortion. Different segmentation analyses also filtered images. Firstly, multiresolution segmentation, maximum spectral difference chessboard performed separate land pixels from ocean ones. Next, Taguchi method was optimise parameters. Subsequently, a support vector machine algorithm optimised segments classify shorelines with an accuracy 98% both Results validated thematic map Department Survey Mapping The change showed average shoreline 12.5 m between 2014. methods developed this demonstrate ability SAR sensors changes, especially during low or high tides tropical regions where passive sensor imagery is often masked by clouds.