Signature Analysis of Targets in PMMW Imagery

M. Stevens and M. Snorrason

IEEE Workshop on Computer Vision Beyond the Visible Spectrum 2001, in conjunction with CVPR in Kauai, Hawaii (December, 2001)

The need for air-to-ground missiles with Autonomous Target Acquisition (ATA) seekers is in large part driven by the failure of pilot-guided bombs in cloudy conditions. Passive-millimeter wave (PMMW) sensors have the ability to see through clouds; in fact they tend to show metallic objects (such as military vehicles) in high contrast regardless of weather conditions. However, their resolution is very low when compared with other popular ATA sensors such as laser-radar (LADAR). Therefore, PMMW imagery is intuitively well suited for detection but not identification. In this paper, we present preliminary detection and segmentation results for a set of image-pairs of military vehicles that were collected for this project using an 89GHz, 18 inch aperture PMMW sensor and a very-high-resolution LADAR. We demonstrate that PMMW sensors show great promise for target detection and for cueing target identification algorithms using higher resolution sensors such as LADAR.

A histogram comparison of the fit model parameters versus ground truth

Request a Copy