Hyperspectral band selection based on the aggregation of proximity measures for automated target detection

John E. Ball; Derek T. Anderson; Sathish Samiappan

doi:10.1117/12.2050638

Translator Disclaimer

13 June 2014 Hyperspectral band selection based on the aggregation of proximity measures for automated target detection

John E. Ball, Derek T. Anderson, Sathish Samiappan

Author Affiliations +

Proceedings Volume 9088, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XX; 908814 (2014) https://doi.org/10.1117/12.2050638
Event: SPIE Defense + Security, 2014, Baltimore, Maryland, United States

Abstract

Band selection is an important unsolved challenge in hyperspectral image processing that has been used for dimensionality reduction and classification improvement. To date, numerous researchers have investigated the unsupervised selection of band groups using measures such as correlation and Kullback-Leibler divergence. However, no clear winner has emerged across data sets and detection tasks. Herein, we investigate the utility of aggregating different proximity measures for band group selection. Specifically, we employ the Choquet integral with respect to different measures (capacities) as it is able to yield a variety of aggregation functions like t-norms, t-conorms and averaging operators. We explore the utility of aggregation in the context of single band, single band group, band group dimensionality reduction and multiple band group combinations in conjunction with support vector machine (SVM) based classification. Our preliminary experiments indicate there is value in aggregating different proximity measures. In some instances an intersection operator works well while in other cases a union operator is best. As may be expected, this can, and does vary per detection task. We also see that depending on the difficulty of the target detection problem, different aggregation, band grouping and combination strategies prevail. Advantages of our approach include; flexibility, the aggregation operator can be learned, and the method can default to a single proximity measure if needed and result, in the worst case, in no performance loss. Experiments are performed on three hyperspectral benchmark data sets to demonstrate the applicability of the proposed concepts.

Citation Download Citation

John E. Ball, Derek T. Anderson, and Sathish Samiappan "Hyperspectral band selection based on the aggregation of proximity measures for automated target detection", Proc. SPIE 9088, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XX, 908814 (13 June 2014); https://doi.org/10.1117/12.2050638

ACCESS THE FULL ARTICLE