Road safety with unmanned aerial vehicle

In daily life, vehicles parked at the pedestrian crossing and people who do not use the pedestrian crossing disrupt the traffic flow, negatively affecting the quality of life, and cause various traffic accidents. The aim of this study is to develop an economical, fast and successful method for detecting pedestrians who do not use the pedestrian crossing and vehicles parked incorrectly by using an Unmanned Aerial Vehicle (UAV). The video stream obtained from the use of the UAV on the determined road route, with a fixed height and angle, was recorded and analyzed with a developed model. The developed model was tested in Ahi Evran University Central Campus. A very high success has been achieved in detecting the faces of people who do not use the pedestrian crossing. Different results have been obtained in detecting the license plates of parked vehicles and also in distinguishing between vehicles parked in places where parking is prohibited and vehicles that make a stop. It is predicted that by using UAVs in daily life in this way, traffic disruptions and accidents can be prevented to a certain extent.