Construction of an Improved Bayesian Clutter Suppression Model for Gas Detection

[摘要] This technical report describes a nonlinear Bayesian Regression model that can be used to estimate effuent concentrations from IR hyperspectral data. As the title implies, the model is constructed to account for background clutter more effectively than current estimators. Although the main objective is to account for background clutter, which is the dominant source of variability in IR data, the model could easily be extended to allow for uncertainties in the atmosphere. The term, "clutter," refers to the variations that occur in the image spectra because emissivity and background temperature change from pixel to pixel. The Bayesian regression model utilizes a more complete description of background clutter to obtain better estimates. The description is in terms of a "prior distribution" on background radiance.

[发布日期] 2002-10-28 [发布机构] Pacific Northwest National Laboratory (U.S.)

[关键词] Mathematical Models Statistics;Statistics;99 General And Miscellaneous//Mathematics, Computing, And Information Science;37 Inorganic, Organic, Physical And Analytical Chemistry;Gases