Recognition and Counting of Citrus Trees Based on UAV Images

Accurate and rapid knowledge of the number of citrus trees is of great significance for predicting citrus yield, managing citrus growth and improving citrus yield. In this paper, the UAV is used to shoot the citrus planting area in Xinhui District of Jiangmen City. The visible light image obtained by the UAV is processed and analyzed by computer vision technology. The number of citrus trees in the shooting area can be accurately obtained, and the number of mature trees and saplings can be further counted. The accuracy rate is more than 95%.The results show that it can meet the requirements of fast and accurate acquisition of citrus trees in planting area at low cost.