Dynamically reconfigurable projection pursuit ensembles for cloud detection in AVIRIS imagery

Charles M. Bachmann, Eugene E. Clothiaux, John W. Moore, Dong Q. Luong

Research output: Contribution to conferencePaperpeer-review

2 Scopus citations


A Projection Pursuit method is used to find structure and reduce the complexity of high-dimensional data (input patches from AVIRIS imagery) by discovering a low-dimensional set of statistically interesting data projections. Individual Projection Pursuit networks in an ensemble focus on one of four spectral bands used in the study. We use preprocessing steps such as Gray-Level Difference Vectors and Sum and Difference Histograms, which are useful for cloud detection. In the past, most work with these particular histogram techniques has involved the extraction of pre-specified moments of the histogram. We show that when each input histogram is treated as a point in a high-dimensional data space, projection pursuit techniques can be used to find an underlying multi-modal structure useful for cloud detection. Because these projection techniques typically have a very large number of parameters, we also examine an online perturbation analysis technique that assesses the relative importance of projection parameters (dynamic reconfiguration). Ensemble methods combine features extracted from AVIRIS imagery by multiple Projection Pursuit networks to obtain pixel classifications using backward error propagation with a cross-entropy objective function. Predicted cloud masks are compared against human interpretation.

Original languageEnglish (US)
Number of pages4
StatePublished - 1995
EventProceedings of the 1995 International Geoscience and Remote Sensing Symposium. Part 1 (of 3) - Firenze, Italy
Duration: Jul 10 1995Jul 14 1995


OtherProceedings of the 1995 International Geoscience and Remote Sensing Symposium. Part 1 (of 3)
CityFirenze, Italy

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • General Earth and Planetary Sciences

Cite this