Image Processing Based Transportation In Unmanned Aerial Vehicles

The use of Unmanned Aerial Vehicles (UAV) has become popular in many fields, especially in the defense industry. Especially in autonomous flights, UAVs that are exposed to variable environmental disruptive effects are shown as a difficult problem to successfully complete their duties. In this study, a high-mobility and low-cost rotary wing UAV with autonomous flight is designed. The UAV, which performs autonomous flight, is intended to recognize and receive 2 different loads of different weight in the cargo receiving area by using image processing methods. In addition, it is aimed to transfer the two loads received by the weight sensor to the weight drop area at a predetermined GPS point by classifying them according to their weight. In the experimental results, it was determined that the UAV successfully recognized the loads, picked them up from the ground and left them by classifying them into the load shedding area. It achieved an average of 90% and 82.5% success in load recognition and classification, respectively.