Detection of Buried Targets via Active Selection of Labeled Data: Application to Sensing Subsurface UXO

摘要

When sensing subsurface targets, such as landmines and unexploded ordnance (UXO), the target signatures are typically a strong function of environmental and historical circumstances. Consequently, it is difficult to constitute a universal training set for design of detection or classification algorithms. In this paper we develop an efficient procedure by which information-theoretic concepts are used to design the basis functions and training set, directly from the site-specific measured data. Specifically, assume that measured data (e.g., induction and/or magnetometer) are available from a given site, unlabeled in the sense that it is not known a priori whether a given signature is associated with a target or clutter. For N signatures the data may be expressed as (x(i) , y(i))(i=1,N), where x(i) is the measured data for buried object i and y(i) is the associated unknown binary label (target/non- target). Let the N x(i) define the set X. The algorithm works in four steps: (1) The Fisher information matrix is used to select a set of basis functions for the kernel-based algorithm, this step defining a set of n signatures B(n) proper subset X that are most informative in characterizing the signature distribution of the site; (2) the Fisher information matrix is used again, to define a small subset X(s) proper subset X, composed of those x(i) for which knowledge of the associated labels y(i) would be most informative in defining the weights for the basis functions in Bn; (3) the buried objects associated with the signatures in X(s) are excavated, yielding the associated labels y(i), represented by the set Y(s); and (4) using B(n), X(s) and Y(s) a kernel-based classifier is designed, for use in classifying all remaining buried objects. This framework is discussed in detail, with example results presented for an actual buried-UXO site.