Aircraft Detection of Remote Sensing Images Based on Faster R-CNN and Yolov3

摘要

With the development of computer vision and satellite remote sensing technology, the intelligent detection of remote sensing image targets has gradually become a hot research topic. In this paper, we investigate two popular deep learning detection methods into aircraft target detection in remote sensing images. The UCAS_AOD-Dataset was expanded and labeled after selection of proper images. Then the two deep learning models, Faster R-CNN and YOLOv3 were trained and validated. The experimental results show that the mAP of Faster R-CNN and YOLOv3 reached 90.06% and 85.98%. Both models can effectively detect aircraft targets.