Its-ny 2013 Best Student Paper Competition Submission Applicant Name

An important aspect of collision avoidance and driver assistance systems, as well as autonomous vehicles, is the tracking of vehicle taillights and the detection of alert signals (turns and brakes). The goal of this paper is to present a novel, robust, and efficient algorithm that is capable of detecting and tracking vehicle taillights, recognizing common alert signals using an embedded smart camera mounted on the vehicle, and counting the cars passing on both sides of the vehicle. This algorithm is implemented in its entirety on a CITRIC embedded smart camera, performs lightweight and reliable detection and tracking from a mobile platform, and can operate under different lighting conditions including daytime and nighttime. The algorithm requires no user intervention, has sophisticated correction mechanisms, and automatically adjusts to varying lighting conditions. In contrast to most existing work that addresses nighttime detection only, the presented algorithm provides the ability to track vehicle taillights and detect alert signals during the day as well, which is inherently more challenging.