A generic framework for context-dependent fusion with application to landmine detection

Abstract

We present a novel method for fusing the results of multiple landmine detection algorithms that use different types of features and different classification methods. Our approach, called Context Extraction for Local Fusion (CELF), is motivated by the fact that the relative performance of different detectors can vary significantly depending on the mine type, geographical site, soil and weather conditions, and burial depth. CELF is a local approach that adapts the fusion method to different regions of the feature space. It is based on a novel objective function that combines context identification and multi-algorithm fusion criteria into a joint objective function. This objective function is defined and optimized to produce contexts via unsupervised clustering while simultaneously providing optimal fusion parameters for each context. Results on large and diverse Ground Penetrating Radar data collections show that the proposed method can identify meaningful and coherent contexts and that different expert algorithms can be identified for the different contexts. Typically, the contexts correspond to groups of alarm signatures that share common attributes such as mine type, geographical site, soil and weather conditions. Our initial experiments have also indicated that the proposed context-dependent fusion outperforms all individual detectors and other standard fusion methods.