Abstract | ||
---|---|---|
Spectral mixture analyses (SMA) is often used as a tool to map complex/mixed (semi-)natural ecosystems. Yet, the performance of SMA, which traditionally uses the amplitude-based RMSE as the objective function, is often hampered by the high spectral similarity among co-occurring plant species. Experiments, based on ray-tracing simulations, in situ measured reflectance data and AVIRIS imagery demonstrated the added value of implementing shape-based error metrics in the unmixing of forests and orchards. The approach allowed to highlight the subtle spectral differences among co-occurring plant species resulting in an overall improvement of species specific mapping (i. e. decrease in MSE ≈ 40%). |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/WHISPERS.2012.6874222 | WHISPERS |
Keywords | Field | DocType |
remote sensing,vegetation,vegetation mapping,aviris imagery,amplitude-based rmse,co-occurring plant species,complex seminatural ecosystem,forest unmixing,mixed seminatural ecosystem,objective function,orchard unmixing,ray-tracing simulations,reflectance data,shape-based error metrics,shape-based unmixing,spectral mixture analysis,hyperspectral,forests,orchards,spectral similarity,hyperspectral imaging,linear programming,shape,accuracy | Vegetation,Remote sensing,Environmental science | Conference |
ISSN | ISBN | Citations |
2158-6268 | 978-1-4799-3405-8 | 0 |
PageRank | References | Authors |
0.34 | 3 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Laurent Tits | 1 | 57 | 10.49 |
Ben Somers | 2 | 269 | 30.34 |
wanda de keersmaecker | 3 | 1 | 1.42 |
gregory p asner | 4 | 123 | 8.69 |
Jamshid Farifteh | 5 | 2 | 1.12 |
Pol Coppin | 6 | 147 | 20.87 |