Automatic Pine Tree Calculation Using You Only Look Once (YOLO)

Counting pine trees from aerial imagery photos is an important challenge in a variety of fields, including ecology, forest management, and climate change Traditional methods of tree counting often require time-consuming and cost-effective field surveys. Therefore, there is a need for a more efficient and accurate method for counting Pine trees from aerial imagery photos. This study has carried out a more efficient and accurate calculation of automatic pine trees, using the YOLOv8 detection model, which aims to detect pine trees by comparing YOLOv8 and Local Maxima in previous studies. The results obtained in this study are that the YOLOv8 model can detect pine tree objects with an accuracy of 88.8%, the precision in the Pines-tree class reaches 88.25 and the recall reaches 96.9%. Meanwhile, for the Null class, the precision value reached 61.5% and the recall reached 81.9%. From the accuracy results obtained, it shows that the YOLOv8 model succeeds in detecting and counting pine trees better than previous studies.