A comprehensive overview of improving traffic flow observability using UAVs as mobile sensors

Unmanned Aerial Vehicles (UAVs) have become a promising topic in many research areas. Applications based on UAV technologies are ranging from traffic surveillance to event observation. This paper is a comprehensive overview for using small UAVs on traffic monitoring to improve traffic flow observability. The existing efforts are mainly choosing quadrotors as a source of raw data because a quadrotor can accurately and efficiently perform tasks that would be of high risk for a human pilot to perform. However, there are some issues on applying quadrotors in data collection such as battery limitation, instability, data transmission, and flight altitude. This paper discusses current limitations and challenges of collecting traffic data using UAVs. This paper also demonstrates an experimental trial in 2017 to show the UAV data collection process along a corridor. Lastly, the paper investigates the potential methods to detect traffic objects using UAV videos