A research on determination of weeds in cotton field via images obtained by rotary wing unmanned aerial vehicle

Data acquisition on pests in agriculture needs to be reliable and fast. One of the technologies that meet this condition and do a lot of work in a short time is the unmanned aerial vehicle (UAV). In this thesis, it was aimed to determine the weeds between rows in cotton plantings with the help of UAV images. The usage areas of UAVs in agriculture are diversifying and expanding day by day. The trial flight was carried out with a rotary-wing quad-rotor with RGB camera UAV. In the trials, the images taken by the UAV camera were transferred to the computer and the images were formatted according to the purpose. These formats have been converted to RED, GREEN, BLUE etc indices. Meteorological conditions were obtained from the UAV application installed on the smartphone. Accordingly, the average meteorological values on the flight day and flight time; The air temperature is 30 oC, the wind speed is 2,7 m/s, the number of satellites connected to the UAV is 17, the visibility is 16 km, and the relative humidity is 18% were recorded. In the trial, UAV images were determined in the 48m^2 (8 m × 6 m) sampling area of the trial plot, at a flight altitude of 1,5 m and a flight speed of 3-5 m/s. As a result of this study, it was concluded that rotary-wing UAVs can be used to determine weeds in cotton field. Keywords: Agriculture, Cotton, Weed, Unmanned Aerial Vehicles, Image Processing.