Application of unmanned aerial vehicles in monitoring of communication routes on country areas

Abstract

Along with intensive development of automotive transport there is a real need of assurance of monitoring for the purpose of the improvement of safety of traffic and to increase the flow of traffic, particularly in the case of large routes. Applying unmanned aerial vehicles (UAVs) equipped with compact digital cameras is an outstanding solution. Currently UAVs are widely used in many areas, particularly in transport. Principal uses encompass the supervision of safety, monitoring of the strain of movement, monitoring of construction of roads and of connected research with the course of communication nets. Selected aspects of applying UAV equipped with compact digital camera for the monitoring traffic flow routes are described in the article. Imagery data were obtained with the fixed-wing Trimble UX-5 platform, which was equipped with the compact digital camera. Analysis of the usefulness of images for the monitoring of the traffic intensity was performed on the selected traffic routes. Detection of vehicles on the video was based on the method of Haar Feature-based Cascade Classifier from the OpenCV collection of a library. The training of the classifier consisted in preparing several dozen different samples containing cars and trucks. After the operation of training the classifier analyzing the chosen sequences of images was possible. The effectiveness of the detection of vehicles at the images deprived of the smear equals 64 %. It is a satisfying result. Considering the fact that images were not made in the nadir they were only obliques. In addition, wooded and urban areas were registered on the images besides the road and vehicles. For that reason the classifier in many cases recognized the crowns of trees as individual vehicles. Research methods applied at the work can be used and tested for the detection of vehicles on roads, like motorways or dual carriageways.