Real Time Computer Vision

This SBIR Phase I project will demonstrate the feasibility and effectiveness of efficient background separation technologies that enable real-time computer vision in mobile sensors and devices. The proposed technologies use advanced mathematical models and subspace estimation algorithms that are several orders-of-magnitude faster than the state-of-the-art methods. Therefore, the proposed technologies do not require hardware optimizations or special computational architectures to achieve real-time performance on a variety of mobile processors. Furthermore, as opposed to many state-of-the-art approaches, they enable background separation on videos from freely moving sensors. The Phase I effort will include; development of proposed background separation algorithms and its enabling technologies, quantitative and qualitative evaluation of the proposed technologies, and demonstration of proof of concept using real-world data from multiple use-cases. The project will benefit from Novateur Teams expertise in background subtraction, automated visual surveillance, and adaptable sensor exploitation.