Multi-sensor and algorithm fusion with the choquet integral: applications to landmine detection

September 20, 2004 in Conference Papers

Abstract:

We discuss the application of Choquet integrals to multi-algorithm and multi-sensor fusion in landmine detection. Choquet integrals are defined. Specific classes of measures, the full and Sugeno measures, are described. Full measures are optimized via quadratic programming. A steepest descent algorithm for optimizing Sugeno measures is derived by applying implicit differentiation. Multiple detection algorithms are applied to hyper-spectral and synthetic aperture radar imagery. In addition, a LWIR vegetation index is computed using statistics of apparent emissivity. The detection algorithms are combined using an OR operator and Choquet integrals with respect to full and Sugeno measures. The Choquet integral with respect to the full measure achieves lower false alarm rates.

Links:

IEEE Link PDF

Citation:

P. Gader, A. Mendez-Vasquez, K. Chamberlin, J. Bolton, and A. Zare, “Multi-sensor and algorithm fusion with the choquet integral: applications to landmine detection,” in IEEE Int. Geoscience and Remote Sens. Symp. (IGARSS), 2004, pp. 1605-1608. 
@InProceedings{gader2004multi,
     Title = {Multi-sensor and algorithm fusion with the choquet integral: applications to landmine detection},
     Author = {Paul Gader and Andres Mendez-Vasquez and Kenneth Chamberlin and Jeremy Bolton and Alina Zare},
     Booktitle = {IEEE Int. Geoscience and Remote Sens. Symp. (IGARSS)},
     Year = {2004},
     Month = {Sept.},
     Pages = {1605-1608},
     Volume = {3},
     Doi = {10.1109/IGARSS.2004.1370635}}