This paper proposes a technique for using infrared (IR) imagery to eliminate false forward-looking ground penetrating radar (FLGPR) detections by examining areas in IR images corresponding to FLGPR alarm locations. The FLGPR and IR co-location is based on the assumption of a flat earth and the pinhole camera model. The parameters of the camera and its location on the vehicle are not assumed to be known. The parameters of the model are estimated using a set of correspondences gathered from the data utilizing the covariance matrix adaptation evolution strategy (CMA-ES) optimization algorithm. Detection of false alarms is accomplished by generating a descriptor, consisting of various statistics calculated from the IR images along with the FLGPR confidence value, for each alarm location. The alarms are then classified based on the Mahalanobis distance between their descriptor and a multivariate normal distribution used to model false alarms. The false alarm distribution is computed from training data where the validity of each alarm location is already known. Using this technique, generally fifteen to twenty percent or more of the FLGPR false alarms can be eliminated without losing any true alarms.
[1]
Nikolaus Hansen,et al.
Completely Derandomized Self-Adaptation in Evolution Strategies
,
2001,
Evolutionary Computation.
[2]
Nikolaus Hansen,et al.
A restart CMA evolution strategy with increasing population size
,
2005,
2005 IEEE Congress on Evolutionary Computation.
[3]
Michael D. Duncan,et al.
Anti-tank and side-attack mine detection with a forward-looking GPR
,
2004,
SPIE Defense + Commercial Sensing.
[4]
Paul D. Gader,et al.
On the confidence level fusion of IR and forward-looking GPR
,
2006,
SPIE Defense + Commercial Sensing.
[5]
Michael D. Duncan,et al.
Mine detection with a forward-looking ground-penetrating synthetic aperture radar
,
2003,
SPIE Defense + Commercial Sensing.