ROBUST THERMOPHYSICS-BASED INTERPRETATION OF RADIOMETRICALLY UNCALIBRATED IR IMAGES FOR ATR AND SITE CHANGE DETECTION

We recently formulated a new approach for computing invariant features from infrared (IR) images, That approach is unique in the field since it considers not just surface reflection and surface geometry in the specification of invariant features, but it also takes into account in ternal object composition and thermal state that affect images sensed in the nonvisible spectrum, In this paper, we extend the thermophysica l algebraic invariance (TAI) formulation for the interpretation of unc alibrated infrared imagery and further reduce the information that is required to be known about the environment, Features are defined such that they are functions of only the thermophysical properties of the i maged objects, In addition, we show that the distribution of the TAI f eatures can be accurately modeled by symmetric alpha-stable models, Th is approach is shown to yield robust classifier performance, Results o n ground truth data and real infrared imagery are presented, The appli cation of this scheme for site change detection is discussed.