Satellite and Unmanned Aerial Vehicle Data for the Classification of Sand Dune Vegetation

Abstract

ABSTRACT:Within coastal systems, sand dunes are the only natural barriers able to counteract erosive processes. Since their equilibrium is often threatened by human activities and high vulnerability of the coastal environment, dunes require increasing attention and specific monitoring. Located between the mainland and the sea, dunes are unique residue habitats for some plant and animal species. In particular, their vegetation is important because it has a consolidation function and promotes the vertical dune accretion. A georeferenced vegetation classification can be useful to define the advancements or erosion stage of the dune, usually based only on the geometric reconstruction. The proposed study aims to compare the classifications performed with some combinations of two of the last generation sensors and traditional image processing techniques. High spectral resolution satellite image (WorldView-2) and a multispectral orthophoto, obtained from data acquired by an unmanned aerial vehicle, were used. Objects and pixel algorithms were applied and the results were compared by a statistical test. Using the same bands, the findings show that both data are suitable for monitoring the evolutionary dune status. Specifically, the WorldView-2 pixel-based classification and UAV object-based classification provide the same accurate results.

Comparison of Pixel- and Object-Based Classification Methods of Unmanned Aerial Vehicle Data Applied to Coastal Dune Vegetation Communities: Casal Borsetti Case Study

“…The International GPS Service for Geodynamics permanent station of Medicina (Bologna, Italy) and the European Reference for Quality Assured Breast Screening and Diagnostic Services permanent station of Porto Garibaldi (Ferrara, Italy) were used to define the positions of the GCPs in the WGS84 system. The chosen projection system is UTM 33N [43].…”

“…Successively, a polygon mash was generated based on the previously built dense point cloud. Finally, the digital surface model and the orthoimage were generated with a resolution of 0.15 m. The orthoimage produced maintained the three channels (i.e., green, red, NIR) that were essential for the later vegetation analysis [43].…”