Comparison of pre-detection and post-detection fusion for mine detection

We present and compare methods for pre-detection (feature-level) and post-detection (decision-level) fusion of multisensor data. This study emphasises methods suitable for data that are non-commensurate and sampled at noncoincident points. Decision-level fusion is most convenient for such data, but this approach is sub-optimal in principle, since targets not detected by all sensors will not achieve the maximum benefits of fusion. A novel feature-level fusion algorithm for these conditions is described. The optimal forms of both decision-level and feature-level fusion are described, and some approximations are reviewed. Preliminary results for these two fusion techniques are presented for experimental data acquired by a metal detector, a ground-penetrating radar, and an infrared camera.