The authors describe a parallel dynamical system designed to integrate model-based and data-driven approaches to image recognition in a neural network, and study one component of the system in detail. That component is the translation-invariant network of probabilistic cellular automata (PCA), which combines feature-detector outputs and collectively performs enhancement and recognition functions. Recognition is a novel application of the PCA. Given a model of the target object, conditions on the PCA weights are obtained which must be satisfied for object enhancement and noise rejection to occur, and engineered weights are constructed. For further refinement of the weights, a training algorithm derived from optimal control theory is proposed. System operation is illustrated with examples derived from visual, infrared, and laser-radar imagery.

We describe the design of an image-recognition system and its performance on multi-sensor imagery.The system satisfies a list of natural requirements, which includes locality of inferences (for efficient VLSI implementation), incorporation of prior knowledge, multi-level hierarchies, and iterative improvement. Two of the most important new features are: a uniform parallel architecture for low-, mid-and high-level vision; and achievement of recognition through short-, as opposed to its long-time behavior, of a dynamical system. Robustness depends on collective effects rather than high precision of the processing elements. Th resulting network displays a balance of high speed and small size. We also indicate how this architecture is related to the Dempster-Shafer calculus for combining evidence from multiple sources, and present novel methods of learning in such networks, including one that addresses the integration of model-based and data-driven approaches.

No abstract

The HTRDLS instrument is an infrared limb-scanning radiometer designed to sound the upper troposphere, stratosphere, and the mesosphere as part of the Chemistry Platform for NASA's Earth Observing System (EOS) Program. The instrument performs limb scans at multiple azimuth angles, measuring CO2. 03, H20, aerosols and other significant greenhouse trace gases in 21 channels ranging from 6. 12 to 17.76pm. The Detector Subsystem (DSS) focal plane assembly (FPA) contains the 2 1 detectors for the science measurements and a set of alignment detectors to be used for instrument integration. All detector elements are Photoconductive HgCdTe operating in the 60-65K range and each channel has a separate cold ifiter. The FPA is mounted in a customized vacuum dewar which couples to a Stirling-cycle mechanical cryocooler via a sapphire rod.Lockheed Martin has designed, fabricated and tested detectors covering the entire HIRDLS spectral range. All the n-type HgCdTe starting material was grown at Lockheed Martin. The vacuum dewar and the preamplifier designs were done at Lockheed Man.In this paper, we will discuss the key features of and design drivers for the DSS design and the design validation activities. The details of the DSS to instrument interfaces will be discussed. We will consider the solutions found for design and packaging issues with the DSS, and the design trades made at the subsystem level to optimize the instrument performance and increase the ease of assembly and instrument integration.

No abstract