A NEUROLOGICALLY-INSPIRED MODEL FOR COMBAT TARGET IDENTIFICATION

SoftThought, Inc. proposes to continue the development of our Advanced Cerebral Emulator (ACE) which models image input as loosely organized shapes. The model is neurologically inspired and reflects the information processing techniques thought to be involved in the human brain. We use our shape analysis system, the Blob Descriptor Language (BDL) to convert salient features of an image into reduced elements for a self-managed database. We then use a convergent neural network for processing this information, behavioral and functionality components which influence the decision-making processes and neural plates which store information about objects in the environment, actions that are available to the model and cause and effect relationsips between the neural plates. When combined with our object image processing, Fast Identification and Tracking (FIT) system , we will be able to identify individual objects in any orientation, with small databases of salient features rapidly in real-time with a microprocessor. We believe that this is tanamount in the preparation for the autonomous exploration of space. This appraoch will explore the use of autonomous vehicles in Phase II with our FIT system onboard to identify targets and will produce a general set of paradigms for fast, accurate and unique image processing.