Investigation of Initialization Strategies for the Multiple Instance Adaptive Cosine Estimator
This work addresses initialization strategies for a specific sensor method in explosive detection, representing an incremental improvement.
The paper tackled the problem of improving initialization for the Multiple Instance Adaptive Cosine Estimator (MI-ACE) in electromagnetic induction sensors for subsurface explosive hazard detection, resulting in evaluation of new techniques based on performance and speed metrics.
Sensors which use electromagnetic induction (EMI) to excite a response in conducting bodies have long been investigated for subsurface explosive hazard detection. In particular, EMI sensors have been used to discriminate between different types of objects, and to detect objects with low metal content. One successful, previously investigated approach is the Multiple Instance Adaptive Cosine Estimator (MI-ACE). In this paper, a number of new initialization techniques for MI-ACE are proposed and evaluated using their respective performance and speed. The cross validated learned signatures, as well as learned background statistics, are used with Adaptive Cosine Estimator (ACE) to generate confidence maps, which are clustered into alarms. Alarms are scored against a ground truth and the initialization approaches are compared.