A comparison of error metrics and constraints for multiple endmember spectral mixture analysis and spectral angle mapper

By Philip E. Dennison, Kerry Halligan, Dar A. Roberts. 2004

387 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Ecology, Media Technology

View Paper: https://www.semanticscholar.org/paper/9d96a5d174bd94f9d3ddc66c4c91f756d76cde21

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Ecology

In Media Technology

Citations in the corpus

Mapping two Eucalyptus subgenera using multiple endmember spectral mixture analysis and continuum-removed imaging spectrometry data (2011, methodology): “…two average spectral similarity metrics, endmember average root mean square error (EAR; Dennison & Roberts, 2003a) and minimum average spectral angle (MASA; Dennison et al., 2004), to select endmembers from the spectral library that were most representative of their species-level vegetation class.”
Comparing endmember selection techniques for accurate mapping of plant species and land cover using imaging spectrometer data (2012, methodology): “Dennison et al. (2004) introduced Minimum Average Spectral Angle (MASA), which functions similarly to EAR but uses spectral angle (Kruse et al., 1993) in place of RMSE.”
Differentiating plant species within and across diverse ecosystems with imaging spectroscopy (2015, methodology): “Many methods exist to select endmembers from a reference spectral library (Dennison et al., 2004), but one developed specifically for classification is Iterative Endmember Selection (IES) (Schaaf, Dennison, Fryer, Roth, & Roberts, 2011).”
A Framework for Automatic and Unsupervised Detection of Multiple Changes in Multitemporal Images (2012, neutral): “olution images [27]–[29]; 2) supervised classification and/or clustering of hyperspectral and multispectral images [30], [31]; 3) supervised CD [32]; 4) spectral unmixing [33], [34]; 5) target”
Recovering missing pixels for Landsat ETM + SLC-off imagery using multi-temporal regression analysis and a regularization method (2013, neutral): “It can be calculated by (Dennison et al., 2004): MSA ¼ XM j¼1 arccos Xn b¼1 NOjNRj= ffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffi Xn b¼1 NOj 2Xn b¼1 NRj 2 vuut 0 @ 1 A 0 @ 1 A=M ð19Þ where n is the total number of bands.”