Paper
30 October 2007 Retrieving vegetation cover types in the complex natural ecosystem of the Pollino National Park (South Italy) through Hyperion data
Author Affiliations +
Abstract
In this paper the potential of the Hyperion spaceborne hyperspectral data in discriminating land covers in complex natural ecosystems was evaluated according to the hierarchical structure of the European standard legend (CORINE Land Cover 2000). Furthermore, the ability of the Hyperion data in retrieving land cover information at sub-pixel level was assessed by exploiting the vegetation classes' distribution as obtained by aerial-photos. Four standard supervised classifiers have been compared in terms of algorithm performance and class accuracy by applying statistical metric; the best results were achieved with the Minimum Distance (MD) classifier. In those areas exhibiting mixed pixels at the Hyperion spatial resolution a Linear Spectral Unmixing technique was applied for deriving abundance fractions of the endmembers (i.e. land covers) previously identified. Accuracy of the un-mixing analysis was evaluated using a Residual Error index calculated by relating Hyperion fractional abundances and reference aerial-photos. Results show the capability of Hyperion data to map land covers and vegetation diversity even at sub-pixel level within a complex natural landscape.
© (2007) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Lorenzo Fusilli, Cristiana Bassani, Simone Pascucci, and Stefano Pignatti "Retrieving vegetation cover types in the complex natural ecosystem of the Pollino National Park (South Italy) through Hyperion data", Proc. SPIE 6749, Remote Sensing for Environmental Monitoring, GIS Applications, and Geology VII, 674930 (30 October 2007); https://doi.org/10.1117/12.739076
Lens.org Logo
CITATIONS
Cited by 1 scholarly publication.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Vegetation

Sensors

Spatial resolution

Satellites

Ecosystems

Environmental monitoring

Remote sensing

Back to Top