Abstract: A system and method for performing Automatic Target Recognition by combining the outputs of several classifiers. In one embodiment, feature vectors are extracted from radar images and fed to three classifiers. The classifiers include a Gaussian mixture model neural network, a radial basis function neural network, and a vector quantization classifier. The class designations generated by the classifiers are combined in a weighted voting system, i.e., the mode of the weighted classification decisions is selected as the overall class designation of the target. A confidence metric may be formed from the extent to which the class designations of the several classifiers are the same. This system is also designed to handle unknown target types and subsequent re-integration at a later time, effectively, artificially and automatically increasing the training database size.

Abstract: A system and method for performing Automatic Target Recognition by combining the outputs of several classifiers. In one embodiment, feature vectors are extracted from radar images and fed to three classifiers. The classifiers include a Gaussian mixture model neural network, a radial basis function neural network, and a vector quantization classifier. The class designations generated by the classifiers are combined in a weighted voting system, i.e., the mode of the weighted classification decisions is selected as the overall class designation of the target. A confidence metric may be formed from the extent to which the class designations of the several classifiers are the same. This system is also designed to handle unknown target types and subsequent re-integration at a later time, effectively, artificially and automatically increasing the training database size.

Abstract: The target identification technology described herein includes a method, a system, and a computer program product. In some examples, the system includes a length estimation module configured to determine a length of a target from a radar image based on a range profile, the radar image, and one or more adaptive parameters. The system can include a points of interest module configured to identify at least one point of interest of the target from the radar image based on the length of the target, the range profile, the radar image, the one or more adaptive parameters, and Hough Line processing. The system can include an identification module configured to determine a target identification from a plurality of identification classes based on the length of the target and the at least one point of interest of the target.

Abstract: The target identification technology described herein includes a method, a system, and a computer program product. In some examples, the system includes a length estimation module configured to determine a length of a target from a radar image based on a range profile, the radar image, and one or more adaptive parameters. The system can include a points of interest module configured to identify at least one point of interest of the target from the radar image based on the length of the target, the range profile, the radar image, the one or more adaptive parameters, and Hough Line processing. The system can include an identification module configured to determine a target identification from a plurality of identification classes based on the length of the target and the at least one point of interest of the target.