Feature level fusion of polarimetric infrared and GPR data for landmine detection

Feature-level sensor fusion is the process where specific information (i.e. features) from objects detected by different sensors are combined and classified. This paper focuses on the feature-level fusion procedure for a sensor combination consisting of a polarimetric infrared (IR) imaging sensor and a GPR: a video impulse radar (VIR). The single sensor detection methods and the featurelevel sensor-fusion methods are evaluated. The detection results of both single sensors and the sensor-fusion methods are presented in receiver operator characteristics (ROC) curves. They show that on the training set featurelevel sensor-fusion always outperforms the best single sensor. Furthermore, on the independent evaluation set there are ROC points of the feature-level sensor-fusion methods that are better than the best sensor.