SBIR-STTR Award

An approach is desired that allows composite infrared background scenes to be synthetically generated using a data base of background objects and types. I-MATH has previously developed an algorithm for a related application, whereby actual scene images are decomposed with a Laplacian pyramid, and then each level in the pyramid is characterized by its second order statistics. Synthetic scene images are synthesized to have the same characteristics, and the synthetic images are determined to be sufficient by a "closeness" algorithm. Before the synthetic generation of backgrounds can be accomplished, a set of background metrics must be identified, I-MATH has been performing research into such metrics for ten years and is very aware of the limitations of such popular parameterizations as the Schmeider-Wethersby metric for describing clutter. For the Schmeider-Wethersby metric, there is no representation of target shape, target internal detail, or background clutter. Hense, against even bland backgrounds, checkerboards can have the same equivalent DT as a uniform target. I-MATH originally addressed this deficiency by adapting a camouflage metric, which convolves the brightness-structured target by the point spread function of the eye (or other sensor), and then computes an equivalent DT using absolute values. In a subsequent development of a Visual Observer Model (VOM), I-MATH incorporated a target-to-background discriminability metric based on cooccurrence metrics. This computes a density of confusing forms (M) and a corresponding discrimination probability (P3). In Phase I, we will evaluate several additional M and equivalent DT metrics. A representative variety of clutter conditions will be considered, giving consideration to a recently developed taxonomy for distinguishing clutter types. The characterization is three dimensional, with the bases related to (1) repetitiveness/fractal (dimension), (2) directionality (gradient), and (3) complexity (granularity). For Phase I, we will use the existing P3 formulation in VOM for computing target discrimination probability. This is an empirically derived and well validated equation for predicting operator image assessment.

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