Aircraft detection using optical remote sensing images and YOLOv7 based deep learning method

Abstract

Target detection is an important application in remote sensing. Aircraft detection in remote sensing images (RSIs) has attracted widespread attention in recent years, which has been widely used in both military and civilian fields. In this study, we used YOLOv7 (You Only Look Once) model for Aircraft detection from satellite images. The results show that YOLOv7 can be well applied in the field of Aircraft detection. The YOLOv7 model with mAP, Precision, Recall, F1 score and average detection time of 95.62%, 93.27%, 93.41%, 93.34% and 0.025 s per image performed well in recognition.