UAV, unmanned aircraft systems, drones, traffic monitoring, incident management, background subtraction algorithm, vehicle detection
Digital Object Identifier (DOI)
During the second phase of this study, the team collected field data with unmanned aerial vehicles (UAVs) at different elevations and distances from the road to analyze the performance of a background subtraction algorithm for vehicle detection. Validation analyses were carried out and their results indicated that a detection rate with an accuracy of up to 92% can be reached using the background subtraction algorithm. The results of the ANOVA test confirmed that the drone’s distance from the road was the only main factor associated with vehicle detection percentage (at the 95% confidence level). It was also determined that, depending on drone type, elevation can affect the detection rate based on the interaction plots created. The experiences from the field activities that took place during this phase of the project were incorporated into the previously developed protocol for the use of UAVs in corridor surveillance. The protocol was also updated with the steps that must be followed for several scenarios and these can be incorporated in future studies on the use of drones in transportation applications.
Was this content written or created while at USF?
Scholar Commons Citation
Cruzado, Ivette; Figueroa-Medina, Alberto M.; González, David R.; Valdés, Didier M.; Rivera-Pérez, Luz G.; and Ruiz-Hernández, Bryan E., "Corridor-Wide Surveillance Using Unmanned Aircraft Systems Phase II: Freeway Incident Detection using Unmanned Aircraft Systems (Part A)" (2023). Research Reports. 19.