The initial six months will apply the same Phase I methodology to additional IR background clutter metrics, as well as using much additional imagery with more prevalent clutter and lower target temperatures. Approximately 64 metric combinations will be evaluated (including the 16 from Phase I) using ROC plots of the Visual Observer Model (VOM) target acquisition probabilities and clutter false alarms. The next six months will entail developing an algebraic/fuzzy logic relationship between the parameters of the image transformer algorithms found to be most effective in discriminating clutter per the ROC analyses. This will be accomplished using the B evolutionary algorithms, which produces the code for combining the metrics, along with a clutter difficulty measure when that metric combination is measured on an image. Using the e results, we will rate a large set of imagery and produce an associated Validation Plan, to be implemented by observer testing at the start of Year Two. The second year will also embody determination of the metrics' suitability for autonomous IR seekers without a man-in-the-loop. Initially, this will be done with computer models, similar in construct to VOM, so that seeker performance probabilities can be computed for detection/recognition, clutter discrimination, and clutter false alarms. The validity of the metrics for seeker applications will be determined using MICOM facilities in the last six months. We anticipate that different sets of metrics/combining relationships may be required for human observers and autonomous seekers. In addition to the metric specifications and associated IR imagery, we will provide all Phase I and fl software in source code, along with a comprehensive User's Manual. Training to use this software will be provided at MICOM at the time of our final presentation, at the end of this two year program.
Benefits: In addition to missile seeker applications, this item can be used on any infrared imaging sensor to improve the sensor performance and improve operator effectiveness. This includes intrusion devices, law enforcement night viewing devices, forest fire detection devices, satellite imagery evaluation, etc. Other markets include machine vision for industrial applications (robotics, automatic assembly, sorting), and medical imaging analysis.
Keywords: clutter metrics focal plane array texture seeker performance