Networked high-speed vision for evasive maneuver assist

Abstract

We propose a framework for evasive maneuver assist using an array of high-speed cameras capable of communicating with each other via a network, called networked high-speed vision. The system has a wide field-of-view and high responsiveness, enabling vehicles to receive information about potential dangers immediately after it appears around them, thus allowing them to perform evasive maneuvering as quickly as possible. We demonstrated the effectiveness of the proposed system in a typical scenario in which evasive maneuvering is performed. Experiments with a robotic car platform and simulations showed that the proposed system outperformed a system composed of a video-rate camera.