Sensor fusion performance gain for buried mine/UXO detection using GPR, EMI, and MAG sensors

Marble, Jay A.; Ackenhusen, John G.; Wegrzyn, John W.; Mancuso, Joseph; Dwan, Chris M.

doi:10.1117/12.396235

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the specific training data used in that work, superior performance was noted for hard decision fusion. Marble et al [14] demonstrated the benefits of using hard decision-level fusion to combine EMI, GPR, and magnetometer data for detection of mines with large metal content. In that work, significant problems with misregistration of noncommensurate sensors were overcome by converting all sensor outputs to a scalar, image-like format and interpolating the result.…”

mentioning

confidence: 99%

Feature-level and decision-level fusion of noncoincidently sampled sensors for land mine detection

Gunatilaka

Baertlein

2001

IEEE Trans. Pattern Anal. Machine Intell.

114

View full text Add to dashboard Cite

AbstractÐWe present and compare methods for feature-level (predetection) and decision-level (postdetection) fusion of multisensor data. This study emphasizes fusion techniques that are suitable for noncommensurate data sampled at noncoincident points. Decision-level fusion is most convenient for such data, but it is suboptimal in principle, since targets not detected by all sensors will not obtain the full benefits of fusion. A novel algorithm for feature-level fusion of noncommensurate, noncoincidently sampled data is described, in which a model is fitted to the sensor data and the model parameters are used as features. Formulations for both featurelevel and decision-level fusion are described, along with some practical simplifications. A closed-form expression is available for feature-level fusion of normally distributed data and this expression is used with simulated data to study requirements for sample position accuracy in multisensor data. The performance of feature-level and decision-level fusion algorithms are compared for experimental data acquired by a metal detector, a ground-penetrating radar, and an infrared camera at a challenging test site containing surrogate mines. It is found that fusion of binary decisions does not perform significantly better than the best available sensor. The performance of feature-level fusion is significantly better than the individual sensors, as is decision-level fusion when detection confidence information is also available (ªsoft-decisionº fusion).

show abstract

mentioning

confidence: 99%