Neural Network for Object Tracking in Congested Environments

Intellisense Systems, Inc. (Intellisense) proposes to develop a new Neural Network for Object Tracking in Congested Environments (NOTICE). NOTICE innovatively utilizes a combination of neural networks to identify and classify cooperative, non-cooperative, or deliberately deceptive targets in the field of view (FOV) of radio frequency (RF) sensors including passive, bi-static, and sensors using synthetic aperture radar with a higher accuracy than conventional approaches. Its unique tracking algorithm employs a combination of neural network and conventional processing to provide real-time tracking in congested environments and is completely scalable, enabling it to track arbitrary numbers of targets without requiring excessive resources while providing performance comparable to existing non-scalable algorithms. Another NOTICE innovation is its dynamic target recognition algorithm, which enables it to recognize and track any object in the FOV, even if the object is not contained within NOTICE’s classification library, ensuring that targets are not missed and allowing the system to adapt to new situations without error. NOTICE accepts RF data streams from any sensor and streams from commercial websites. In Phase I, Intellisense will describe the NOTICE architecture and concept of operations applicable to missile defense applications and missions, as well as develop the initial NOTICE algorithms and demonstrate their abilities to distinguish between similar objects and to track objects of interest. In Phase II, Intellisense will develop a complete prototype system and demonstrate its ability to detect, track, and identify objects in a congested environment using available data streams, such as from commercial airport and seaport websites. Intellisense will also reach out to manufacturers of systems relevant to missile defense to begin transitioning NOTICE to a product. Approved for Public Release | 22-MDA-11215 (27 Jul 22)