Ground vehicle detection and classification by an unmanned aerial vehicle

摘要

Rotary-wing unmanned aerial vehicles (UAV) are being widely used in different applications due to its several features, such as mobility, lightweight, embedded processing and capability of flying in different height levels. Among the possible applications they are used in surveillance tasks, agriculture environments monitoring, power lines inspections and diseases detection in crops. The images captured by the UAVs need to be examined in most of the applications. This analysis is usually done by experts, but a system that process the captured images in a autonomous way can speed up the results and more images can be processed in a lesser period, which is the ideal for real time applications. This work presents a system for vehicle detection aiming at surveillance task. The system is evaluated in terms of precision of detection of a particular type of vehicle. The video was shot using a monocular camera coupled with an aerial robot developed in our Lab. The experimental results demonstrate that the proposed system can be used for the vehicles tracking task under controlled conditions.