Support vector machines for hyperspectral remote sensing classification

J. Anthony Gualtieri; Robert F. Cromp

doi:10.1117/12.339824

Translator Disclaimer

29 January 1999 Support vector machines for hyperspectral remote sensing classification

J. Anthony Gualtieri, Robert F. Cromp

Author Affiliations +

Proceedings Volume 3584, 27th AIPR Workshop: Advances in Computer-Assisted Recognition; (1999) https://doi.org/10.1117/12.339824
Event: The 27th AIPR Workshop: Advances in Computer-Assisted Recognition, 1998, Washington, DC, United States

Abstract

The Support Vector Machine provides a new way to design classification algorithms which learn from examples (supervised learning) and generalize when applied to new data. We demonstrate its success on a difficult classification problem from hyperspectral remote sensing, where we obtain performances of 96%, and 87% correct for a 4 class problem, and a 16 class problem respectively. These results are somewhat better than other recent result on the same data. A key feature of this classifier is its ability to use high-dimensional data without the usual recourse to a feature selection step to reduce the dimensionality of the data. For this application, this is important, as hyperspectral data consists of several hundred contiguous spectral channels for each exemplar. We provide an introduction to this new approach, and demonstrate its application to classification of an agriculture scene.

Citation Download Citation

J. Anthony Gualtieri and Robert F. Cromp "Support vector machines for hyperspectral remote sensing classification", Proc. SPIE 3584, 27th AIPR Workshop: Advances in Computer-Assisted Recognition, (29 January 1999); https://doi.org/10.1117/12.339824

ACCESS THE FULL ARTICLE